Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-01T01:55:40.954429Z
Paper Citation Record · LEDGER
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
As of 22 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2606.30755.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T15:24:58.168172Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-15T15:24:58.605043Z
Reference resolution
41 of 41 outbound references displayed
- verified exact15
- verified fuzzy22
- unresolved3
- parse uncertain1
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 56f8772b-707b-4eed-8d44-cb598fc4d8c4 · outbound
This paper cites Anderson.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Anderson
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.531952Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation b886d389-6932-4ec6-8fa8-330641a89986 · outbound
This paper cites AgentHarm: A benchmark for measuring harmfulness of LLM agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens AgentHarm: A benchmark for measuring harmfulness of LLM agents
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.575809Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation d1233e5c-85ae-4812-a336-5a1cc61522e6 · outbound
This paper cites Elliott Bell and Leonard J.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Elliott Bell and Leonard J
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.579392Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 7f626961-77a4-476a-8d55-d44916006756 · outbound
This paper cites an unresolved cited work.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Unresolved cited work
Reference 4
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T05:23:21.573234Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 007fe01d-9370-45aa-8385-babca95f8a33 · outbound
This paper cites arXiv preprint arXiv:2602.14364 , year =.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens arXiv preprint arXiv:2602.14364 , year =
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.135898Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 61809342-c090-44fc-b436-49c801e7c72e · outbound
This paper cites Ai agent security risks in 2026: The incident landscape and hardening frame- work.https://blog.cyberdesserts.com/ai-agent-security-risks/, 2026.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Ai agent security risks in 2026: The incident landscape and hardening frame- work.https://blog.cyberdesserts.com/ai-agent-security-risks/, 2026
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.568390Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 92690f93-2922-41dd-8b37-d1bcea9bf473 · outbound
This paper cites AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.570756Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 9e3742ea-69f6-4f18-acc3-d6efc11e25b7 · outbound
This paper cites OpenClawCVEs: Tracking OpenClaw CVEs.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens OpenClawCVEs: Tracking OpenClaw CVEs
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.582955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 4d40fbeb-2690-45f1-aacd-56445c903333 · outbound
This paper cites From Model Scaling to System Scaling: Scaling the Harness in Agentic AI.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.138803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 6bc7b6df-6a65-475a-a9a1-ae92555460c6 · outbound
This paper cites Model context protocol (mcp): Landscape, security threats, and future research directions.ACM Transactions on Software Engineering and Methodology.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Model context protocol (mcp): Landscape, security threats, and future research directions.ACM Transactions on Software Engineering and Methodology
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.563153Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 923539c2-5742-46d0-af7e-78ef16a73d6f · outbound
This paper cites Malicious openclaw ‘skill’ targets crypto users on clawhub — 14 malicious skills were uploaded to clawhub last month.Tom’s Hardware, 2026.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Malicious openclaw ‘skill’ targets crypto users on clawhub — 14 malicious skills were uploaded to clawhub last month.Tom’s Hardware, 2026
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.560017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation e549a117-edb4-48d6-9020-bfdfacde4cc9 · outbound
This paper cites arXiv preprint arXiv:2603.11088 , year =.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens arXiv preprint arXiv:2603.11088 , year =
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.142429Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation d63eed7b-99d5-4ffe-a184-807998d7b851 · outbound
This paper cites Breaking the protocol: Security anal- ysis of the model context protocol specification and prompt in- jection vulnerabilities in tool-integrated llm agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Breaking the protocol: Security anal- ysis of the model context protocol specification and prompt in- jection vulnerabilities in tool-integrated llm agents
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.145114Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a4f686f0-3c5f-4308-b650-c74fedf05447 · outbound
This paper cites an unresolved cited work.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T05:23:21.551627Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 4c8f4c13-13ea-4fab-bb35-b363d60ff614 · outbound
This paper cites Running openclaw safely: identity, isolation, and runtime risk.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Running openclaw safely: identity, isolation, and runtime risk
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.520391Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 2c531b0c-71ed-45f7-a0a4-2f37cb8e87a8 · outbound
This paper cites Nvidia nemoclaw: Reference stack for running openclaw in openshell.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Nvidia nemoclaw: Reference stack for running openclaw in openshell
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.546801Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 0c54f5cc-6fb2-421d-9015-70a62ad008f7 · outbound
This paper cites Claudy day: Chaining prompt injection and data exfiltration in claude.ai.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Claudy day: Chaining prompt injection and data exfiltration in claude.ai
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.549353Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a6aae13d-96ea-42ef-8783-02b44392636e · outbound
This paper cites SLSA: Supply-chain levels for software artifacts.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens SLSA: Supply-chain levels for software artifacts
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.554147Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 9bfa8c4c-75c6-4778-82d6-95390a5e7356 · outbound
This paper cites Security (gateway).https://docs.openclaw.ai/, 2026.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Security (gateway).https://docs.openclaw.ai/, 2026
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.556621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a021e2c9-8bb1-4bda-af71-933f3815aa85 · outbound
This paper cites an unresolved cited work.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T05:23:21.525503Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation c8f4f7a5-8634-4051-a7b3-e90297d4395a · outbound
This paper cites OW ASP top 10 for large language model applications.https://owasp.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens OW ASP top 10 for large language model applications.https://owasp
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.542199Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation e45d1b88-3aaa-4058-885a-18c244ff9f99 · outbound
This paper cites OW ASP top 10 for agentic applications.https://genai.owasp.org/ resource/owasp-top-10-for-agentic-applications-for-2026/, 2026.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens OW ASP top 10 for agentic applications.https://genai.owasp.org/ resource/owasp-top-10-for-agentic-applications-for-2026/, 2026
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.527644Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 8f095242-0e49-4e3e-9505-a7999fdb5c34 · outbound
This paper cites Coding agents: A comprehensive survey of automated bug fixing systems and benchmarks.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Coding agents: A comprehensive survey of automated bug fixing systems and benchmarks
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.534612Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 3c0ad7d4-7be4-4a2c-8edc-07ed474961b5 · outbound
This paper cites Securing LLM Agents Need Intent-to-Execution Integrity.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Securing LLM Agents Need Intent-to-Execution Integrity
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.144513Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 0d5bd4df-7ea2-4ed4-b803-8c97fcf48342 · outbound
This paper cites MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.121509Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a618e25f-ce8a-440e-8b4c-bc7caf12edbc · outbound
This paper cites Maddison, and Tatsunori Hashimoto.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Maddison, and Tatsunori Hashimoto
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.536753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 4d417c3c-8727-4def-bdef-738a55776df0 · outbound
This paper cites SeClaw: Secured personal ai assistant.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens SeClaw: Secured personal ai assistant
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.544537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 022a633c-0e79-4eff-976d-3dbd4bc4a8bf · outbound
This paper cites an unresolved cited work.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Unresolved cited work
Reference 28
- Resolution
- parse uncertain
- raw_fallback, observed 2026-07-07T05:23:21.529927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 128c7f5c-8402-4895-92d3-a4105ec52873 · outbound
This paper cites Saltzer and Michael D.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Saltzer and Michael D
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.539122Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 75fbd36b-c2a4-43cb-9569-5d5e430825ff · outbound
This paper cites Openclaw — personal ai assistant.github, 2026.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Openclaw — personal ai assistant.github, 2026
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.565750Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 75049aa2-db5b-41ba-ae8c-0c534c3b874f · outbound
This paper cites SafeArena: Evaluating the Safety of Autonomous Web Agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens SafeArena: Evaluating the Safety of Autonomous Web Agents
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.148105Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation f5cfd133-5294-43c7-a576-eefe60423d0f · outbound
This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.139809Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation b568f65d-78e7-427b-937b-51875cd5d806 · outbound
This paper cites arXiv preprint arXiv:2602.10453 , year=.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens arXiv preprint arXiv:2602.10453 , year=
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.120350Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation e004d1e8-1c78-4e15-b925-48ccc13fea18 · outbound
This paper cites A Systematic Security Evaluation of OpenClaw and Its Variants.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens A Systematic Security Evaluation of OpenClaw and Its Variants
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.125751Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 29644b9c-1388-481e-8824-bcedde026de9 · outbound
This paper cites ClawSafety: "Safe" LLMs, Unsafe Agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens ClawSafety: "Safe" LLMs, Unsafe Agents
Reference 35
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.133228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 6d8fb2c5-780e-4420-8260-0c41ba7fd405 · outbound
This paper cites SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.111703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 81371c37-faa0-4534-8242-97af9ac154da · outbound
This paper cites R-Judge: Benchmarking safety risk awareness for LLM agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens R-Judge: Benchmarking safety risk awareness for LLM agents
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.586086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 72f6a7bd-1506-4b72-b096-2e03dcc4ccac · outbound
This paper cites InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T05:23:21.523289Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 52618e1e-d08c-4721-9348-cff9c83832eb · outbound
This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 39
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.115038Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 84cd81f1-3234-471e-a3b9-7b5e116226cf · outbound
This paper cites Deep Research: A Survey of Autonomous Research Agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Deep Research: A Survey of Autonomous Research Agents
Reference 40
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T12:35:44.109156Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a9c00921-aa68-4452-96e6-705831a906c8 · outbound
This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Agent-SafetyBench: Evaluating the Safety of LLM Agents
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.141583Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Pith citing papers
Observation c67d2e8c-4ba8-4929-85e9-1e07cf112899 · inbound
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems cites this paper.
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-08-15T15:24:58.609051Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.