crewai

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains standard documentation and code examples for the CrewAI framework. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
  • [PROMPT_INJECTION]: No evidence of instructions attempting to bypass safety guidelines or override agent behavior was found.
  • [DATA_EXFILTRATION]: No hardcoded credentials or sensitive file access patterns were detected. The network-enabled tools mentioned (SerperDevTool, WebsiteSearchTool) are standard components of the CrewAI ecosystem.
  • [REMOTE_CODE_EXECUTION]: No patterns for downloading and executing untrusted code or arbitrary commands were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:09 PM
Security Audit — agent-trust-hub — crewai