AlphaUncommon
Agent-Threat-Rule/agent-threat-rules
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
- Owner
- Agent-Threat-Rule (organization)
- Stars
- Stars: 424
- Forks
- Forks: 66
- Language
- TypeScript
- License
- MIT
- Created
- 2026
- Topics
- agent-securityai-securityllm-securitymcp-securityowaspprompt-injectionsigma-rulesthreat-detectiongarakowasp-agentic
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in TypeScript
All TypeScript repos- msk1039/nagomiStars: 424TypeScriptAlpha
- Parcha-ai/agentrunStars: 424TypeScriptAlpha
- antfu/furifontStars: 424TypeScriptAlpha
- apollographql/persistgraphqlStars: 424TypeScriptAlpha
- huan/node-facenetStars: 424TypeScriptAlpha
- atularen/ngx-monaco-editorStars: 424TypeScriptAlpha