crewai

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill assigns researcher agents web-search tools (e.g., SerperDevTool, WebsiteSearchTool and the WebSearchTool implementation calling search_api.search(query) in references/patterns.md) and uses research flows that ingest those search results, so agents fetch and read content from public websites (untrusted third‑party content) as part of their workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:38 AM