source-gathering
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime the workflow uses public web/paper search tools (e.g., brave-search, apify, semantic-scholar) to fetch outsider-authored pages/papers and then calls
wiki-ingest-sourceto ingest their readable text into “source pages,” which the agent can later include in LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata