awesome-llm-agent-security
github.com/wearetyomsmnv/awesome-llm-agent-security ↗All about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.
53
GitHub Stars
41
Curated Resources
2
Categories
22 hours ago
Last Refreshed
Security Landscape📚 Research & Publications
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me 🔒 owasp top 10 for ai agents (non official) resources from awesome-llm-agent-security"
Installation instructions →What's inside
Security Landscape
- AAC-01🔒 OWASP Top 10 for AI Agents (Non official)
Unauthorized control of agent actions
- ACS-02🔒 OWASP Top 10 for AI Agents (Non official)
Unsafe interaction with critical systems
- AGI-03🔒 OWASP Top 10 for AI Agents (Non official)
Malicious modification of agent objectives
- AHE-04🔒 OWASP Top 10 for AI Agents (Non official)
Exploitation of agent's false assumptions
- AIC-05🔒 OWASP Top 10 for AI Agents (Non official)
Cascading effects of agent actions
- AKP-10🔒 OWASP Top 10 for AI Agents (Non official)
Contamination of agent's knowledge base
📚 Research & Publications
- Agent-Attack
Attack Testing
- Agent Behavior Study
arXiv
- Agentic AI: New Frontier
AI Security Union
- Agent Security Analysis
arXiv
- Agent-Smith
Agent security testing
- Agent Threat Rules (ATR)
Open-source AI agent security detection rules
Showing a sample of 41 resources. View the full list on GitHub →