agent-threat-rules
Open detection standard -- like Sigma, but for AI agents. 655 rules for prompt injection, tool poisoning, context exfiltration, and MCP attacks. Shipped in Cisco AI Defense. 97.2% recall on NVIDIA garak.
Version 3.5.2 License MIT
Keywords
ai-securityagent-securityprompt-injectionsigma-rulesthreat-detectionmcp-securityllm-securityatr
INSTALL
Top version - 0
Full agent-threat-rules Download Stats 
ShareKeywords
ai-security
agent-security
prompt-injection
sigma-rules
threat-detection
mcp-security
llm-security
atr
Get a badge for your package
