Vibe Coding Discoverawesome-agent-skills-security
View on GitHub🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems
A curated directory of research, standards, benchmarks, and tools for securing AI agents and their skills. Covers attacks such as prompt injection and tool poisoning, plus defenses including access control, sandboxing, validation, and red teaming.
Use Cases
Research prompt injection risks in tool-using agentsAssess malicious skills and plugin supply-chain threatsFind agent security benchmarks and datasetsCompare defenses such as sandboxing and access controlDevelop threat models for AI agent systemsExplore MCP server security research
Built With
- Frameworks
- OWASP Agentic AI Threats and Mitigations · OWASP Top 10 for LLM Applications · OWASP Agentic Skills Top 10 · MITRE ATLAS · NIST AI Risk Management Framework · NIST SP 800-218A
Tags
agent security · LLM security · prompt injection · tool-use security · skill security · MCP security · AI safety · red teaming · security benchmarks · supply-chain security