crewai

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional content and code examples for the CrewAI framework. Analysis of the instructions, YAML configurations, and Python code snippets revealed no malicious patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a vulnerability surface common to multi-agent frameworks that ingest external data.
  • Ingestion points: The skill demonstrates agents using SerperDevTool and WebsiteSearchTool to retrieve content from the internet (SKILL.md).
  • Boundary markers: Absent; the provided code templates do not explicitly show delimiters or instructions to ignore malicious content within tool outputs.
  • Capability inventory: Agents are configured to perform web searches and process the results to generate content (SKILL.md).
  • Sanitization: Absent; the skill focuses on framework orchestration rather than input validation or sanitization techniques for retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:31 PM
Security Audit — agent-trust-hub — crewai