agent-threat-rules

@Agent-Threat-Rule

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.

MIT Commit 1 dag geleden ★ 402

Pijlers en weging

Soevereiniteit 30% 48

Onderhoud 25% 100

Beveiliging 20% geen gegevens

Adoptie 15% 13

Open standaarden 10% 0

Waarom deze score

MIT (permissief)
Laatste commit 0 dagen geleden
Uitgebracht in de afgelopen 12 maanden
Top 87% naar sterren in Beveiliging & identiteit › Security Operations

Feiten

Licentie: MIT (Permissief)
Taal: TypeScript
GitHub-sterren: 402
Laatste commit: 2026-09-27 (1 dag geleden)
Laatste release: 2026-08-23T07:34:40Z
OpenSSF Scorecard: Nog niet gemeten
Zelf hosten: Niet vastgesteld
Maintainer-locatie: Onbekend
Bron: github-crawl,github-search

Alternatieven in Security Operations

pentagi

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

77 02

open-kritt

Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

77 03

vuls

Agent-less vulnerability scanner for Linux, FreeBSD, Container, WordPress, Programming language libraries, Network devices

76 04

Shuffle

Shuffle: A general purpose security automation platform. Our focus is on collaboration and resource sharing.