# Source Links

This public site keeps source links and derived wiki notes. Local PDF archives
and full extracted text dumps are intentionally not published.

| Source | Archive URL | Wiki page |
| --- | --- | --- |
| A2ASecBench | [OpenReview](https://openreview.net/forum?id=LfdFnakqGJ) | [A2ASecBench](wiki/sources/a2asecbench.md) |
| A Security Analysis of the OpenClaw AI Agent Framework | [arXiv:2603.27517](https://arxiv.org/abs/2603.27517) | [OpenClaw security analysis](wiki/sources/openclaw-security-analysis.md) |
| ClawWorm | [arXiv:2603.15727](https://arxiv.org/abs/2603.15727) | [ClawWorm](wiki/sources/clawworm.md) |
| Uncovering Security Threats and Architecting Defenses in Autonomous Agents | [arXiv:2603.12644](https://arxiv.org/abs/2603.12644) | [OpenClaw threats and FASA](wiki/sources/openclaw-threats-fasa.md) |
| Security Threat Modeling for Emerging AI-Agent Protocols | [arXiv:2602.11327](https://arxiv.org/abs/2602.11327) | [Agent protocol threat modeling](wiki/sources/agent-protocol-threat-modeling.md) |
| Skill-Inject | [arXiv:2602.20156](https://arxiv.org/abs/2602.20156) | [Skill-Inject](wiki/sources/skill-inject.md) |
| Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems | [arXiv:2604.03081](https://arxiv.org/abs/2604.03081) | [Skill supply-chain poisoning](wiki/sources/skill-supply-chain-poisoning.md) |
| Do Not Mention This to the User | [arXiv:2602.06547](https://arxiv.org/abs/2602.06547) | [Malicious agent skills](wiki/sources/malicious-agent-skills.md) |
| CaMeLs Can Use Computers Too | [arXiv:2601.09923](https://arxiv.org/abs/2601.09923) | [CaMeLs CUA security](wiki/sources/camels-cua-security.md) |
| AgentSentinel | [arXiv:2509.07764](https://arxiv.org/abs/2509.07764) | [AgentSentinel](wiki/sources/agentsentinel.md) |
| RedTeamCUA | [arXiv:2505.21936](https://arxiv.org/abs/2505.21936) | [RedTeamCUA](wiki/sources/redteamcua.md) |