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.
Agent-Threat-Rule/agent-threat-rules has 427 GitHub stars. It gained +2 stars over 3 recorded days in the last 7 days (snapshots through Nov 9, 2026).
Its biggest recent day was Nov 5, 2026, with +1 stars.
It currently ranks #40059 daily, #4251 weekly, #5035 monthly by momentum on Trending Repos; its best-ever rank is #2876.
Trending Repos first recorded it on May 15, 2026.
| Date | Stars gained | Total stars | Forks gained |
|---|---|---|---|
| +1 | 427 | +2 | |
| 0 | 426 | 0 | |
| +1 | 425 | 0 |