crewai
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill serves as a legitimate educational resource for the CrewAI library.
- [INDIRECT_PROMPT_INJECTION]: The provided code examples use template variables (e.g.,
{topic}) to interpolate data into agent goals and task descriptions. While this is a common ingestion point for external data, it is a standard architectural feature of the CrewAI framework and does not represent an exploited vulnerability in this context.
Audit Metadata