AgentSafeLabs

AgentSafeLabs/safelabs-eval

OWASP ASI-aligned red-teaming and evaluation framework for AI agents

11 stars 4 forks 11 watchers Python Apache License 2.0
agent-security ai-safety crewai evaluation jailbreak langchain llm-security owasp prompt-injection red-teaming
View on GitHub Website
1 Open Issue Need Help Last updated: Aug 28, 2026

Open Issues Need Help

View All on GitHub
Proposal: EvalPort adapter for safelabs-eval (PromptEntry/EvalRecord/EvalResult → TestCase/GraderResult/ResultSet) about 2 hours ago
good first issue
AgentSafeLabs/safelabs-eval
11

OWASP ASI-aligned red-teaming and evaluation framework for AI agents

Python
#agent-security#ai-safety#crewai#evaluation#jailbreak#langchain#llm-security#owasp#prompt-injection#red-teaming