crewai
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for CrewAI agents and tasks that interpolate external data into prompts, creating a surface for indirect instructions.
- Ingestion points: User-supplied variables (e.g.,
{topic}) are interpolated into agent goals inconfig/agents.yamland task descriptions inconfig/tasks.yaml. - Boundary markers: The provided examples do not use delimiters or specific prompt engineering to distinguish between instructions and data.
- Capability inventory: Agents defined in the skill have access to search tools like
SerperDevToolandWebsiteSearchTooland can execute multi-step logic viacrew.kickoff()increw.py. - Sanitization: The skill does not provide examples or instructions for sanitizing or validating the input data before interpolation.
Audit Metadata