Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-27T12:53:33.800969Z
Paper Citation Record · LEDGER
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
As of 16 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 4 inbound Pith citation observations for arXiv:2606.10484.
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 2026-08-16T06:30:59.297886+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T19:23:23.346372Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-10T18:36:42.753993Z
Reference resolution
27 of 27 outbound references displayed
- verified exact12
- verified fuzzy0
- unresolved10
- parse uncertain0
- malformed identifier0
- metadata mismatch5
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 5f086488-5852-4517-ab2c-aeb39d3c610b · outbound
This paper cites Accessed: 2026-05-04.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Accessed: 2026-05-04
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 193b13bc-78b0-4066-b58c-9534e688ef79 · outbound
This paper cites Accessed: 2026-05-04.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Accessed: 2026-05-04
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 03aea92e-7c5c-46b2-8fdf-b5a2db447cd1 · outbound
This paper cites Mind the gap: Text safety does not transfer to tool-call safety in llm agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Mind the gap: Text safety does not transfer to tool-call safety in llm agents
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T06:07:41.486758Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 81e45a2c-de6d-41ca-9856-f2cad7f535f6 · outbound
This paper cites Taming OpenClaw: Security analysis and mitigation of autonomous LLM agent threats.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Taming OpenClaw: Security analysis and mitigation of autonomous LLM agent threats
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T06:07:41.489277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 0e0ddb34-c0e9-4b46-a8b4-acfad86dee59 · outbound
This paper cites ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T06:07:41.481734Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation ff4906c2-75f6-4039-a1ab-78401fea3b8b · outbound
This paper cites Accessed: 2026-05-04.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Accessed: 2026-05-04
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 339e7326-7b82-4170-bda0-c6fd59d8a8e3 · outbound
This paper cites AlphaEvolve: A coding agent for scientific and algorithmic discovery.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments AlphaEvolve: A coding agent for scientific and algorithmic discovery
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T06:07:41.484161Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 4bdf0a36-2edd-4e2f-85ab-e37bd62e6122 · outbound
This paper cites Accessed: 2026-05-04.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Accessed: 2026-05-04
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cb25c529-9ab0-49a9-b890-8269391df712 · outbound
This paper cites X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T06:07:41.477969Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 520ca1f0-3d46-4d9c-a05d-e3e4c4a68a65 · outbound
This paper cites Identifying the risks of lm agents with an lm-emulated sandbox.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Identifying the risks of lm agents with an lm-emulated sandbox
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d5fbc939-fbe3-4cc3-83bd-24b05a3b5bab · outbound
This paper cites Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.501052Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation fb7bf7de-c693-43c8-9eb7-b795e45e0c9c · outbound
This paper cites Don’t let the claw grip your hand: A security analysis and defense framework for OpenClaw.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Don’t let the claw grip your hand: A security analysis and defense framework for OpenClaw
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T06:07:41.503816Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 313875b0-513e-4417-93f3-b6321397d259 · outbound
This paper cites Agents of Chaos.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Agents of Chaos
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.492542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 7705d572-61bf-4a7f-9603-706edca13b6d · outbound
This paper cites arXiv preprint arXiv:2512.16962 , year=.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments arXiv preprint arXiv:2512.16962 , year=
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T06:07:41.480446Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 02eee7be-d9d9-4da8-90db-2f390fe6e858 · outbound
This paper cites URLhttps://arxiv.org/abs/2601.05504 First Author et al.:Preprint submitted to ElsevierPage 20 of 21 Security, Privacy, and Ethical Risks in OpenClaw.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments URLhttps://arxiv.org/abs/2601.05504 First Author et al.:Preprint submitted to ElsevierPage 20 of 21 Security, Privacy, and Ethical Risks in OpenClaw
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T06:07:41.466880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 67a1275e-639f-4f94-9afb-d9a7b5ec9a83 · outbound
This paper cites ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.471435Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation a9e50ba7-bdda-47e4-b38f-e728e5b113e3 · outbound
This paper cites 28 Xilong Wang, John Bloch, Zedian Shao, Yuepeng Hu, Shuyan Zhou, and Neil Zhenqiang Gong.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments 28 Xilong Wang, John Bloch, Zedian Shao, Yuepeng Hu, Shuyan Zhou, and Neil Zhenqiang Gong
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b236a70-7887-456a-9452-5bffc1711795 · outbound
This paper cites OpenClaw-RL: Train Any Agent Simply by Talking.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments OpenClaw-RL: Train Any Agent Simply by Talking
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.495761Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 513add2a-8e81-4d1f-bb01-2b57d2a9a61e · outbound
This paper cites ClawSafety: "Safe" LLMs, Unsafe Agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments ClawSafety: "Safe" LLMs, Unsafe Agents
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.498652Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation a49362a0-25f7-4029-a039-b0e4aa0123b5 · outbound
This paper cites Toolsafety: A comprehensive dataset for enhancing safety in llm-based agent tool invocations.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Toolsafety: A comprehensive dataset for enhancing safety in llm-based agent tool invocations
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 876c6ca4-f5d5-47f6-af89-492a463d9772 · outbound
This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T06:07:41.460941Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 761b640e-6c22-403a-a8b1-90b11f8ecd51 · outbound
This paper cites Accessed: 2026-05-04.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Accessed: 2026-05-04
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae43f29e-99a5-45f5-af85-55c8487c4094 · outbound
This paper cites GLM-5: from Vibe Coding to Agentic Engineering.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments GLM-5: from Vibe Coding to Agentic Engineering
Reference 23
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T06:07:41.476720Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation bc58e92b-3234-4a55-9c2d-bf5a44f4d13f · outbound
This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9705c800-7c6c-4ee6-82a1-59a7df39af38 · outbound
This paper cites Agent security bench (asb): Formalizing and benchmarking attacks and defenses in llm-based agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Agent security bench (asb): Formalizing and benchmarking attacks and defenses in llm-based agents
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T12:53:33.800969Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dead27c0-f681-4e55-aef9-017f725fba2d · outbound
This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Agent-SafetyBench: Evaluating the Safety of LLM Agents
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.482603Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation fc3c8ab7-283d-45e3-9733-5f8f60aba316 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T06:07:41.479229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Pith citing papers
Observation 0decaa8a-667e-46b5-95ec-54a8fcf22785 · inbound
Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models cites this paper.
Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T08:29:25.498449Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85ab5460-39c1-419d-86fe-9ac4ff47a0bc · inbound
Where Is the Cost of Third-Party API Routers in Agentic Software Development? cites this paper.
Where Is the Cost of Third-Party API Routers in Agentic Software Development? AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-07-30T17:25:46.911432Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1e9bb2e3-ac67-41a0-bd4f-9459b7ab749b · inbound
Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework cites this paper.
Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
Reference 19
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-10T18:36:42.761618Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 5cf22db1-1859-4bb3-a4a3-2882e2601706 · inbound
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents cites this paper.
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T19:23:23.346372Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.