Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions | Paper Citation Record

Observation 86f37c4f-1884-4e09-b220-754276836fd1 · outbound

This paper cites https://cloud.google.com/blo g/products/ai-machine-learning/announcing -official-mcp-support-for-google-services ,.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions https://cloud.google.com/blo g/products/ai-machine-learning/announcing -official-mcp-support-for-google-services ,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.365809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d5d45bef-e1a8-40dd-a484-3e88192450c9 · outbound

This paper cites an unresolved cited work.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Unresolved cited work

Reference 2

Resolution: parse uncertain; raw_fallback, observed 2026-07-09T10:26:11.292714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a641013b-596b-414e-8b75-5a1a2d12dacd · outbound

This paper cites https://modelcontextprotoc ol.io/, 2026.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions https://modelcontextprotoc ol.io/, 2026

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.287838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 75fb2810-f13a-4d3d-bc8c-f8cfef765e7a · outbound

This paper cites https://developers.notion.com/gu ides/mcp/mcp, 2026.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions https://developers.notion.com/gu ides/mcp/mcp, 2026

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.289598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 73cd9182-a013-4b35-98ec-280ded097c4e · outbound

This paper cites Introducing the model context protocol,.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Introducing the model context protocol,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.294533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7d789469-39e1-47a0-9a64-9dac2bea922f · outbound

This paper cites URL: https://www.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions URL: https://www

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.291120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3a08c7c8-d3b7-4805-818e-fc299e5bcdae · outbound

This paper cites AgentBound: Securing Execution Boundaries of AI Agents.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions AgentBound: Securing Execution Boundaries of AI Agents

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.091011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c2f12b9e-0562-4aa4-b787-5e3404fb5a81 · outbound

This paper cites Jail- breaking black box large language models in twenty queries.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Jail- breaking black box large language models in twenty queries

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.350082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 89ee4932-e0ad-4eab-831e-e61d49505e89 · outbound

This paper cites MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.138455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c7419c8-0ec8-444e-94a7-9ed978ec58ab · outbound

This paper cites Operation mango: Scal- able discovery of {Taint-Style} vulnerabilities in binary firmware services.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Operation mango: Scal- able discovery of {Taint-Style} vulnerabilities in binary firmware services

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.342820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 075a5ae4-3710-46f6-9f41-ced4b259223a · outbound

This paper cites Github rest api documentation, version 2022-11-28.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Github rest api documentation, version 2022-11-28

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.339312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4cfb941e-ec8f-4738-befa-474dda9ce44b · outbound

This paper cites {PAPILLON}: Efficient and stealthy fuzz {Testing-Powered} jailbreaks for {LLMs}.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions {PAPILLON}: Efficient and stealthy fuzz {Testing-Powered} jailbreaks for {LLMs}

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.344672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ffb2b17a-f47e-4bb0-921d-ec836354d30f · outbound

This paper cites A mea- surement study of model context protocol.arXiv e- prints, pages arXiv–2509, 2025.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions A mea- surement study of model context protocol.arXiv e- prints, pages arXiv–2509, 2025

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.330149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 06864fc7-4354-4245-a7bb-5c6f82afa0b2 · outbound

This paper cites Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.108251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9f603c25-5019-40be-886a-f5dcbaf6ef4f · outbound

This paper cites Vmud: Detecting recurring vulnerabili- ties with multiple fixing functions via function selection and semantic equivalent statement matching.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Vmud: Detecting recurring vulnerabili- ties with multiple fixing functions via function selection and semantic equivalent statement matching

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.335556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation df8c99ce-93e4-49fa-afd2-8dd1142c4d31 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.105580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a54c2a52-a9cd-497d-afa7-33e08bda3492 · outbound

This paper cites Improved Techniques for Optimization-Based Jailbreaking on Large Language Models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.110965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dff32abf-9b9c-4f1e-9608-f89d07010ccf · outbound

This paper cites Artprompt: Ascii art-based jailbreak attacks against aligned llms.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Artprompt: Ascii art-based jailbreak attacks against aligned llms

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.363861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 131859ff-39ca-439a-9563-a4448fb649ce · outbound

This paper cites Mcip: Protecting mcp safety via model contextual integrity protocol.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Mcip: Protecting mcp safety via model contextual integrity protocol

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.309039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c982375e-af73-496c-bc96-ecab86413e48 · outbound

This paper cites PhD thesis, Massachusetts Institute of Technology, 2024.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions PhD thesis, Massachusetts Institute of Technology, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.360396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 844536b1-09bd-4708-bd08-fa34ad0e56c9 · outbound

This paper cites Scaling javascript abstract interpretation to detect and exploit node.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Scaling javascript abstract interpretation to detect and exploit node

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.358712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 90de3d33-348c-410b-9840-3dcff0ee2a6d · outbound

This paper cites Break the breakout: Reinventing lm defense against jailbreak attacks with self-refine.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Break the breakout: Reinventing lm defense against jailbreak attacks with self-refine

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.356904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7fcce9d9-0859-4eb1-94ae-65d4e74112df · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Certifying LLM Safety against Adversarial Prompting

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.133047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d3c27c3e-b0b9-4695-88e9-324a89886159 · outbound

This paper cites MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.140975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 51bd7601-cec7-4c16-bbe0-59cb12db8c25 · outbound

This paper cites Don’t believe everything you read: Understanding and measuring mcp behavior under misleading tool descriptions.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Don’t believe everything you read: Understanding and measuring mcp behavior under misleading tool descriptions

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-09T10:26:11.127212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8da03fe5-b62e-4cb6-8183-73a255208089 · outbound

This paper cites A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.130168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 89c3dcf4-ffd1-417b-a40f-6c8c5ae0646c · outbound

This paper cites Detecting taint-style vulnerabilities in microservice- structured web applications.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Detecting taint-style vulnerabilities in microservice- structured web applications

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.355188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 47fe5c76-8247-4739-b2f6-8666146b07e2 · outbound

This paper cites Make agent defeat agent: Au- tomatic detection of {Taint-Style} vulnerabilities in {LLM-based} agents.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Make agent defeat agent: Au- tomatic detection of {Taint-Style} vulnerabilities in {LLM-based} agents

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.337506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 68b2a687-5108-4de5-aeae-f12dbe607ce1 · outbound

This paper cites Demystifying rce vulnerabilities in llm- integrated apps.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Demystifying rce vulnerabilities in llm- integrated apps

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.341072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 10c1243c-9f0d-4b93-9105-de4f7277c99d · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.113478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4c609c3-9fbe-4a30-aca5-76cfa293053a · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.116509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation afc4bb3e-5998-433c-87ed-209bf101134a · outbound

This paper cites Tchecker: Precise static inter-procedural analysis for detecting taint-style vulnerabilities in php applications.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Tchecker: Precise static inter-procedural analysis for detecting taint-style vulnerabilities in php applications

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.348281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c4949f0c-03c9-418b-a025-311e3d14a1fd · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems, 37:61065–61105.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems, 37:61065–61105

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.328262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c3dfce9-04a1-42ba-8f48-5bb74b19a45f · outbound

This paper cites When a patch goes bad: Exploring the properties of vulnerability-contributing commits.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions When a patch goes bad: Exploring the properties of vulnerability-contributing commits

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.331876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2367be71-dafb-461b-b7a6-bfae44b2739f · outbound

This paper cites Llama guard 4: Model card and prompt formats,.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Llama guard 4: Model card and prompt formats,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.326441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b981fb98-3efe-43a9-bef2-8290edd27f75 · outbound

This paper cites an unresolved cited work.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-07-09T10:26:11.324801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba526d9b-bce5-4d32-8c1d-c409da66c327 · outbound

This paper cites Llama prompt guard: Model cards and prompt formats, 2025.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Llama prompt guard: Model cards and prompt formats, 2025

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.323223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 071e67a4-4a53-4164-98ce-46244f864c5f · outbound

This paper cites MITRE ATT&CK: Adversarial Tactics, Techniques, and Common Knowledge.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions MITRE ATT&CK: Adversarial Tactics, Techniques, and Common Knowledge

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.333748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 695de742-49a5-42d4-93d9-e7786f2f51e0 · outbound

This paper cites Model context protocol python sdk.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Model context protocol python sdk

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.346416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0eaf3218-7fd5-4ea0-90a5-f4f4f38a7789 · outbound

This paper cites National vulnerability database (nvd).

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions National vulnerability database (nvd)

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.367539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ad98be59-7344-4fe1-840c-92b2efb58b7e · outbound

This paper cites Commit 0284aa8 for patching the cve- 2025-5276 vulnerability, 2026.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Commit 0284aa8 for patching the cve- 2025-5276 vulnerability, 2026

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.311000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d0ba8bff-aeba-4d94-98e4-f613c0e32b1f · outbound

This paper cites Cve-2025-5276 detail, 2026.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Cve-2025-5276 detail, 2026

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.312627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac61eb5a-b42c-472b-8618-da0af895e1b2 · outbound

This paper cites User comment of the commit 0284aa8 for patching the cve-2025-5276 vulnerability, 2026.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions User comment of the commit 0284aa8 for patching the cve-2025-5276 vulnerability, 2026

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.307222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e52bc7ad-a364-46b2-9fcc-31a1a41d37ef · outbound

This paper cites The official website of GPT-4o.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions The official website of GPT-4o

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.305393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0fe96147-08d8-4f22-be23-e2face468fcf · outbound

This paper cites Prompt-to-sql injections in llm-integrated web applications: Risks and defenses.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Prompt-to-sql injections in llm-integrated web applications: Risks and defenses

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.353480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a7dfcbde-f276-42c0-8bab-8a0cc5a0ef85 · outbound

This paper cites LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T10:26:11.119011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20025c90-a9b7-42a7-a3f7-03b9dac8dba1 · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.121826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 887d4b74-a026-4320-af9d-284df020920e · outbound

This paper cites do anything now.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions do anything now

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.351746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55f074e0-e5d1-4b25-8844-cffc760c8ac6 · outbound

This paper cites Security debt in llm agent applications: A measurement study of vulnerabilities and mitigation trade-offs.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Security debt in llm agent applications: A measurement study of vulnerabilities and mitigation trade-offs

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.362208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f0896815-4e07-4608-a0a2-a08e267f52a6 · outbound

This paper cites Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.080465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 982000e7-e4da-4df6-a95e-f0f70bc679b1 · outbound

This paper cites Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.067163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 19aa4470-ea30-49c3-818f-d6dc7fe5333e · outbound

This paper cites Mpma: Preference manipulation attack against model context protocol.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Mpma: Preference manipulation attack against model context protocol

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-07-09T10:26:11.088303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 121b3da8-53a6-49bf-a5ae-cf67e5e61b74 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.097166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 46d9247e-4d0d-4ab7-82b2-8400a257fc6f · outbound

This paper cites Silent taint-style vulnerability fixes identifica- tion.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Silent taint-style vulnerability fixes identifica- tion

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.317940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 36847b7f-d5f7-4c8d-8b88-2ee2ff781ab6 · outbound

This paper cites Defending chatgpt against jailbreak attack via self- reminder.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Defending chatgpt against jailbreak attack via self- reminder

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.316172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 16da57ed-0554-4a76-8423-15c438fd1fa4 · outbound

This paper cites MCPZoo: A large-scale dataset of runnable model context protocol servers for AI agent.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions MCPZoo: A large-scale dataset of runnable model context protocol servers for AI agent

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-07-09T10:26:11.102968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b6636e53-8ae4-48db-8c14-99ee20cf4ff5 · outbound

This paper cites Commitshield: Tracking vulner- ability introduction and fix in version control systems.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Commitshield: Tracking vulner- ability introduction and fix in version control systems

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.321365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4a0abde9-6f48-43d5-9558-4d97d687ef0e · outbound

This paper cites Mcpmark: A benchmark for stress-testing realistic and comprehensive mcp use.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Mcpmark: A benchmark for stress-testing realistic and comprehensive mcp use

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-07-09T10:26:11.100117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2b7f3724-c1f7-4827-84f9-4551451be5d9 · outbound

This paper cites Mcp-guard: A defense framework for model context protocol integrity in large language model applications.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Mcp-guard: A defense framework for model context protocol integrity in large language model applications

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-07-09T10:26:11.135889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9b8158fa-3122-4265-9352-6051edadf0a9 · outbound

This paper cites Automatic inference of search patterns for taint-style vulnerabilities.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Automatic inference of search patterns for taint-style vulnerabilities

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.319641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 143b9b97-b693-4c2e-8d11-4a5f08341a9e · outbound

This paper cites The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.085614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b46294dd-b4ef-4c4c-9254-7a0fd48029c4 · outbound

This paper cites Mcpsecbench: A systematic security benchmark and playground for testing model context protocols.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Mcpsecbench: A systematic security benchmark and playground for testing model context protocols

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-09T10:26:11.083158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5cce09c2-c0be-408b-af97-a9315ccddb6b · outbound

This paper cites Precise discovery of more taint-style vulnerabilities in embedded firmware.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Precise discovery of more taint-style vulnerabilities in embedded firmware

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.314445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b8b7a5d9-06d6-497d-ac9b-cd082d2e9672 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Low-Resource Languages Jailbreak GPT-4

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.124368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cad5c47d-60ec-4fe1-940c-e6166fd0bca7 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.094533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 00a75fa0-8811-4429-af8d-9251dc60770c · outbound

This paper cites Don’t listen to me: Understanding and exploring jailbreak prompts 13 of large language models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Don’t listen to me: Understanding and exploring jailbreak prompts 13 of large language models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.301676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 962a42cb-4562-4ad7-841a-b05e624492e8 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.075003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76ce3ab6-7f0e-4037-867e-0f9786f8a039 · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to chal- lenge ai safety by humanizing llms.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions How johnny can persuade llms to jailbreak them: Rethinking persuasion to chal- lenge ai safety by humanizing llms

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.298094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 820b58bb-20bb-41c9-82a6-f5c7487c9d40 · outbound

This paper cites AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.077468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4fff98bb-d63c-4dad-84ba-33277a7a35d2 · outbound

This paper cites Zhang, Z.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Zhang, Z

Reference 70

Resolution: metadata mismatch; arxiv_id, observed 2026-07-09T10:26:11.072266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9774f6cb-1d32-4537-b403-38ec4d020f65 · outbound

This paper cites Statically discov- ering high-order taint style vulnerabilities in os kernels.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Statically discov- ering high-order taint style vulnerabilities in os kernels

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.299937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dc761625-76ea-431b-a4e0-356dbda7926c · outbound

This paper cites Intention analysis makes llms a good jailbreak defender.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Intention analysis makes llms a good jailbreak defender

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.303518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation be738356-2d49-4057-9a75-a9086bb30c9a · outbound

This paper cites Defending large language models against jailbreaking attacks through goal priori- tization.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Defending large language models against jailbreaking attacks through goal priori- tization

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:26:11.296292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8935ad23-5e17-49c4-a9ff-1faf3909d134 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.069633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers