Homepage

agent-threat-rules

Open detection standard -- like Sigma, but for AI agents. 683 rules for prompt injection, tool poisoning, context exfiltration, and MCP attacks. Shipped in Cisco AI Defense. 97.2% recall on NVIDIA garak.

< Back for full overview of agent-threat-rules vulnerabilities

Package versions

50 VERSIONS IN TOTAL
versionpublisheddirect vulnerabilities
3.5.65 Jul, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.5.55 Jul, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.5.41 Jul, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.5.330 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.5.221 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.5.121 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.5.015 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.4.013 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.3.111 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.3.011 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.2.05 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.1.14 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.1.04 Jun, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
3.0.529 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
2.2.112 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
2.1.512 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
2.1.311 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
2.1.211 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
2.1.110 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L
2.1.09 May, 2026
  • 0
    C
  • 0
    H
  • 0
    M
  • 0
    L

Automatically find and fix vulnerabilities affecting your projects. Snyk scans for vulnerabilities and provides fixes for free.

Get started free