AIPython★ 829⑂ 86 forksApache-2.0
AgentSafeLabs/safelabs-eval
PROTECTION OF AI AGENTS FROM THREATS
safelabs-eval — framework for red‑teaming and evaluation of AI agent protection based on the ASI01–ASI10 taxonomy inspired by OWASP. Written in Python, it supports CrewAI and LangChain, enables conducting jailbreak‑tests and vulnerability assessment.
// KEY FEATURES
- Performs red‑teaming scenarios using ASI01–ASI10 taxonomy to uncover vulnerabilities
- Integrates with CrewAI and LangChain for orchestrating multi‑agent workflows
- Generates reports on jailbreak‑attack success rates and coverage of ASI categories
- Runs via CLI, provides a Python SDK and JSON schema for test suite customization
#agent-security#ai-safety#crewai#evaluation#jailbreak#langchain#llm-security#owasp#prompt-injection#red-teaming
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram