Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents | Paper Citation Record

Observation 6325995f-bcba-4904-9719-c869eddb0d9f · outbound

This paper cites infosecurity-magazine.com/news/ 91-of-apt-attacks-start-with-a-spear-phishing/ , 2012.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents infosecurity-magazine.com/news/ 91-of-apt-attacks-start-with-a-spear-phishing/ , 2012

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.200866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2fb8f170-7167-45c9-a293-09886f92b949 · outbound

This paper cites https://www.paubox.com/blog/ the-email-connection-with-atp-attacks , 2023.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://www.paubox.com/blog/ the-email-connection-with-atp-attacks , 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.184103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0bb9c941-fb87-4299-8cef-6fc719a3d2d5 · outbound

This paper cites https://github.com/ transitive-bullshit/agentic, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ transitive-bullshit/agentic, 2025

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.166448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a3e333ff-e6b7-477f-82cd-5937bcabf11f · outbound

This paper cites https://github.com/ aiwaves-cn/agents, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ aiwaves-cn/agents, 2025

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.149457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b37628b6-6efd-4ba5-836d-7edf0ac29f85 · outbound

This paper cites https://docs.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://docs

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.133888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 337266e5-4e21-4224-ac68-eadb16b0bb87 · outbound

This paper cites https://github.com/HKUDS/ AutoAgent, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/HKUDS/ AutoAgent, 2025

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.119874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c31d47cb-e53f-4048-8ae0-da64d5f57be2 · outbound

This paper cites https://github.com/ deepseek-ai/DeepSeek-R1, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ deepseek-ai/DeepSeek-R1, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.103738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 00df22cf-646e-4139-9857-8b9cd7b6dde4 · outbound

This paper cites https://github.com/ deepseek-ai/DeepSeek-V3, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ deepseek-ai/DeepSeek-V3, 2025

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.087541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c4759c04-b8b6-494b-9e21-5f13db739875 · outbound

This paper cites https://ai.google.dev/ gemini-api/docs/models?authuser=1# gemini-1.5-pro, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://ai.google.dev/ gemini-api/docs/models?authuser=1# gemini-1.5-pro, 2025

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.071198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ba818543-c5ad-4c39-b1e4-55883bef6a99 · outbound

This paper cites https://ai.google.dev/ gemini-api/docs/models?authuser=1# gemini-2.0-flash, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://ai.google.dev/ gemini-api/docs/models?authuser=1# gemini-2.0-flash, 2025

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.055478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 43acee7e-2371-4ffe-ad92-ef800d56c240 · outbound

This paper cites https://github.com/, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/, 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.037870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e59f635a-055b-4158-8b83-97bc395cfeca · outbound

This paper cites https://github.com/griptape-ai/ griptape, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/griptape-ai/ griptape, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.022706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d6377911-5b69-4071-a8f6-ada44c15ba9d · outbound

This paper cites https://github.com/deepset-ai/ haystack, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/deepset-ai/ haystack, 2025

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:57.006723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 65c9a792-6ac1-498b-93ee-f3342b48a841 · outbound

This paper cites https://huggingface.co/, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://huggingface.co/, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:56.991661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 38379a74-07ae-4628-9e8f-bac969167e68 · outbound

This paper cites https://github.com/InternLM/ lagent, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/InternLM/ lagent, 2025

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:56.975802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ac9ab31a-59aa-4c05-b1d2-ef1e8eac7fe8 · outbound

This paper cites https://github.com/ langchain-ai/langchain, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ langchain-ai/langchain, 2025

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:56.959184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c4b42c7d-0607-4fb7-a58b-57977d943f40 · outbound

This paper cites https://smith.langchain.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://smith.langchain

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:56.680071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fd510ae5-9a4f-45ff-87b9-2880b2328439 · outbound

This paper cites https://github.com/langflow-ai/ langflow, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/langflow-ai/ langflow, 2025

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:56.537349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3caa2be8-a194-4254-9a1e-2113c9034922 · outbound

This paper cites https://github.com/langroid/ langroid, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/langroid/ langroid, 2025

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:56.155932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 01bcf1c5-64f9-43f0-af4b-541025c769f5 · outbound

This paper cites https://github.com/letta-ai/letta, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/letta-ai/letta, 2025

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:55.864637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 38880e9b-03fa-43da-a984-ab025b1572c6 · outbound

This paper cites https://ollama.com/library/ llama3, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://ollama.com/library/ llama3, 2025

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:55.594134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 774fb88d-fe6f-4edb-a053-bc88d3cd2c6f · outbound

This paper cites https://ollama.com/library/ llama3.1, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://ollama.com/library/ llama3.1, 2025

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:55.355031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bea1b2e8-b021-42bd-90a9-0d0424e4133c · outbound

This paper cites https://ollama.com/library/ llama3.3, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://ollama.com/library/ llama3.3, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:55.224468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5dff1aad-8de1-4b4b-a9bd-6f2ecbebfb1d · outbound

This paper cites https://github.com/ run-llama/llama_index, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ run-llama/llama_index, 2025

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:55.093764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f560ce3f-5cb2-49b2-b965-662037b18a0d · outbound

This paper cites https://github.com/geekan/ MetaGPT, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/geekan/ MetaGPT, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.966057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 331e9879-3cfb-42c6-bc72-15c6f2bbccc9 · outbound

This paper cites https://github.com/ modelscope/modelscope-agent, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ modelscope/modelscope-agent, 2025

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.835577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b6c73ce3-92b6-4b32-aff2-36df355b3ee0 · outbound

This paper cites https://github.com/ openai/openai-agents-python, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://github.com/ openai/openai-agents-python, 2025

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.715219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0bce9e23-2835-4030-926d-d028ee04c4db · outbound

This paper cites https://platform.openai.com/docs/ models/gpt-3.5-turbo, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://platform.openai.com/docs/ models/gpt-3.5-turbo, 2025

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.596039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8527c0bf-9b8a-4209-9c7f-d05b6bd568d8 · outbound

This paper cites https://platform.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents https://platform

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.473543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 28bd2bc9-173b-41c9-af0e-7a66edf6af81 · outbound

This paper cites Ackerman and Nina Panickssery.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Ackerman and Nina Panickssery

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.353565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 58a7e9f8-9ba4-426e-8abc-a23f8db8a107 · outbound

This paper cites Many-shot jail- breaking.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Many-shot jail- breaking

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.223491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc430696-05d6-4676-8570-a877ef986f86 · outbound

This paper cites Encrypted prompt: Securing llm applications against unauthorized actions, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Encrypted prompt: Securing llm applications against unauthorized actions, 2025

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:54.092528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3e565e81-465f-446c-8cbd-c6f4da856a0a · outbound

This paper cites The obvious invisible threat: Llm-powered gui agents’ vulnerability to fine-print injections, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents The obvious invisible threat: Llm-powered gui agents’ vulnerability to fine-print injections, 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:53.985800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3cd1eda8-e905-493b-ad6f-1e7677a8f15e · outbound

This paper cites Struq: Defending against prompt injection with structured queries, 2024.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Struq: Defending against prompt injection with structured queries, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:53.879562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 76bd1828-0218-462d-8737-aa3c0025ec07 · outbound

This paper cites Secalign: Defending against prompt injection with preference optimization, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Secalign: Defending against prompt injection with preference optimization, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T20:29:42.698878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbaaacc6-72b5-485a-9f17-57ad00d65d9f · outbound

This paper cites Can indirect prompt injection attacks be detected and removed? arXiv preprint arXiv:2502.16580, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Can indirect prompt injection attacks be detected and removed? arXiv preprint arXiv:2502.16580, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T20:29:42.762552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5fa52d-0cce-4114-b75d-a6121d7e76ac · outbound

This paper cites Masterkey: Automated jail- breaking of large language model chatbots.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Masterkey: Automated jail- breaking of large language model chatbots

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:53.692485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7212e946-f51d-4d77-aec2-a859e482d917 · outbound

This paper cites The philosopher’s stone: Trojaning plugins of large language models, 2024.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents The philosopher’s stone: Trojaning plugins of large language models, 2024

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:53.546757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3675e98e-101b-42b6-a65d-b12b8f88ca0b · outbound

This paper cites Feature-aware mali- cious output detection and mitigation, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Feature-aware mali- cious output detection and mitigation, 2025

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:53.353399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1993f9fb-3a22-488e-9ff7-887d5ddd11db · outbound

This paper cites Struphantom: Evo- lutionary injection attacks on black-box tabular agents powered by large language models, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Struphantom: Evo- lutionary injection attacks on black-box tabular agents powered by large language models, 2025

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:53.161565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1ec37b72-d1b2-4469-ac11-d096bc0e9d8d · outbound

This paper cites From assistants to agents in the llm era.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents From assistants to agents in the llm era

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:52.976226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 68b1a2c1-d589-42f8-9cc2-abe895d9eea8 · outbound

This paper cites Jbfuzz: Jailbreaking llms efficiently and effectively using fuzzing, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Jbfuzz: Jailbreaking llms efficiently and effectively using fuzzing, 2025

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:52.796476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6c00e9a3-881b-49cb-a6f7-454fe4817775 · outbound

This paper cites Safety mis- alignment against large language models.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Safety mis- alignment against large language models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:52.643089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9359093f-91d3-431a-b0b8-019c3f96d4b9 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:52.438121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1a92068a-1488-49d7-af50-b7e8402adefe · outbound

This paper cites Bypassing prompt injection and jailbreak detection in llm guardrails, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Bypassing prompt injection and jailbreak detection in llm guardrails, 2025

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:52.299856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1e5ae241-bfc9-46e4-a51c-82545cb68c5a · outbound

This paper cites Iterative prompting with persuasion skills in jailbreaking large language models, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Iterative prompting with persuasion skills in jailbreaking large language models, 2025

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:52.144885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 567dc867-d669-4c51-9e67-ec1fe3fe60e0 · outbound

This paper cites xjailbreak: Representation space guided reinforce- ment learning for interpretable llm jailbreaking, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents xjailbreak: Representation space guided reinforce- ment learning for interpretable llm jailbreaking, 2025

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:51.962477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fdf92076-e0e8-4924-bc8f-353d12be5035 · outbound

This paper cites Multi- step jailbreaking privacy attacks on chatgpt, 2023.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Multi- step jailbreaking privacy attacks on chatgpt, 2023

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:51.787327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b5bda01e-3335-406a-828e-2ec43b2bb0f8 · outbound

This paper cites Separator injection attack: Uncovering dialogue bi- ases in large language models caused by role sepa- rators, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Separator injection attack: Uncovering dialogue bi- ases in large language models caused by role sepa- rators, 2025

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:51.629786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 97dfebd2-8523-436b-b47a-4cb616b04a95 · outbound

This paper cites Pico: Jailbreaking multimodal large language models via Pictorial Code contextu- alization, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Pico: Jailbreaking multimodal large language models via Pictorial Code contextu- alization, 2025

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:51.447062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2a7b2de6-f4f2-4289-b7cd-31c969ff61da · outbound

This paper cites Token-level constraint bound- ary search for jailbreaking text-to-image models, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Token-level constraint bound- ary search for jailbreaking text-to-image models, 2025

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:51.253691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1740c6d6-dc88-40e8-94d8-aa6d04e59478 · outbound

This paper cites Demystifying rce vulnerabil- ities in llm-integrated apps.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Demystifying rce vulnerabil- ities in llm-integrated apps

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:51.095063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation df3427e0-fa28-4fcc-bae9-c4db0edd6c3b · outbound

This paper cites Prompt injection attack against llm-integrated ap- plications, 2024.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Prompt injection attack against llm-integrated ap- plications, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:50.888421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 40c9801e-07f1-4885-96dd-84ec5d5d3409 · outbound

This paper cites Formalizing and bench- marking prompt injection attacks and defenses, 2024.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Formalizing and bench- marking prompt injection attacks and defenses, 2024

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:50.658678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0fe7c87b-91b5-40d4-9ab9-d7b153f000b0 · outbound

This paper cites Saro: Enhancing llm safety through reasoning- based alignment, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Saro: Enhancing llm safety through reasoning- based alignment, 2025

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:50.482598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 07fa3256-f73c-4154-b81f-5dc740010e0a · outbound

This paper cites From prompt injections to sql injec- tion attacks: How protected is your llm-integrated web application?, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents From prompt injections to sql injec- tion attacks: How protected is your llm-integrated web application?, 2025

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:50.302309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2f368d73-52b3-4171-9242-a776c8310e1d · outbound

This paper cites Ignore previous prompt: Attack techniques for language models, 2022.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Ignore previous prompt: Attack techniques for language models, 2022

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:50.132083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 98aa6921-b5c0-48a2-a1f7-b80e57bc40b6 · outbound

This paper cites do anything now.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents do anything now

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T20:29:45.022255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ff28be2-30ac-40ee-b2a7-5f860b628710 · outbound

This paper cites Yurascanner: Leveraging llms for task-driven web app scanning.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Yurascanner: Leveraging llms for task-driven web app scanning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:49.892278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2770a61e-afd2-4bbc-bacb-e3a6d55156bd · outbound

This paper cites Signed-prompt: A new approach to prevent prompt injection attacks against llm- integrated applications, 2024.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Signed-prompt: A new approach to prevent prompt injection attacks against llm- integrated applications, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:49.743513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ca85aaf5-dc65-4e4c-8bae-159225f744f0 · outbound

This paper cites Email spoofing with smtp smuggling: How the shared email infrastructures magnify this vul- nerability.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Email spoofing with smtp smuggling: How the shared email infrastructures magnify this vul- nerability

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:49.455967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 66654049-a55d-47a4-9268-f6e8dcb8456c · outbound

This paper cites Unity is strength: Collaborative llm-based agents for code reviewer recommendation.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Unity is strength: Collaborative llm-based agents for code reviewer recommendation

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:49.254390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 420d02d8-212b-450e-be02-532d989229e1 · outbound

This paper cites Geneshift: Impact of different scenario shift on jailbreaking llm, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Geneshift: Impact of different scenario shift on jailbreaking llm, 2025

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:49.077460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 865a1c7f-6f5d-4a34-88a1-7508db99206b · outbound

This paper cites Isolategpt: An exe- cution isolation architecture for llm-based agentic systems, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Isolategpt: An exe- cution isolation architecture for llm-based agentic systems, 2025

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:48.790571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 02f6f7fc-17ff-437b-bc69-8975d2d0be6e · outbound

This paper cites Sneakyprompt: Jailbreaking text-to- image generative models, 2023.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Sneakyprompt: Jailbreaking text-to- image generative models, 2023

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:48.568558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 65d2f12b-a647-4e6b-9d70-b340a8604391 · outbound

This paper cites Lightdefense: A lightweight uncertainty-driven defense against jailbreaks via shifted token distribution, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Lightdefense: A lightweight uncertainty-driven defense against jailbreaks via shifted token distribution, 2025

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:48.369862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4110b923-f0b8-4f1c-b6bc-dbcbbf45c732 · outbound

This paper cites Poster: Repairing bugs with the introduction of new variables: A multi-agent large language model.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Poster: Repairing bugs with the introduction of new variables: A multi-agent large language model

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:48.090922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bc87a13f-3c4b-420e-bc3d-e9bb14c7b73d · outbound

This paper cites Agent security bench (asb): Formalizing and benchmarking attacks and de- fenses in llm-based agents, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Agent security bench (asb): Formalizing and benchmarking attacks and de- fenses in llm-based agents, 2025

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:47.918350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0d2f0ea6-0c43-4bea-917e-4f4caa148c3c · outbound

This paper cites TrojanSQL: SQL injection against natural language interface to database.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents TrojanSQL: SQL injection against natural language interface to database

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:47.712482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4f4e8509-459a-40be-bc90-9fbef5a3554d · outbound

This paper cites Im- perceptible content poisoning in llm-powered ap- plications.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Im- perceptible content poisoning in llm-powered ap- plications

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:47.428850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e081e15d-0047-4019-9041-beef43bafbfd · outbound

This paper cites Defense against prompt injection attacks via mixture of encodings, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Defense against prompt injection attacks via mixture of encodings, 2025

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:47.222555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8dfd4b89-4f76-4898-83f9-af1da43350a3 · outbound

This paper cites On large lan- guage models’ resilience to coercive interrogation.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents On large lan- guage models’ resilience to coercive interrogation

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:47.066157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d447a5c3-abd9-4602-b2e8-fc2008f2aca0 · outbound

This paper cites Adasteer: Your aligned llm is inherently an adaptive jailbreak defender, 2025.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Adasteer: Your aligned llm is inherently an adaptive jailbreak defender, 2025

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:46.936132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 58d8b4bb-de90-4ebd-94c3-71d9b7da2cd2 · outbound

This paper cites [AGENT_NAME].

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents [AGENT_NAME]

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:29:46.758523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 88a1f251-e6d5-49d6-944e-6fb98bc18a56 · outbound

This paper cites an unresolved cited work.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Unresolved cited work

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T20:29:46.060837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0d95ebe-01c9-4a61-bb29-f48f17396fcb · outbound

This paper cites an unresolved cited work.

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T20:29:45.840643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers