best-practice-research
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill is a wrapper that routes “external evidence” gathering to
researcher, which at runtime would typically fetch and ingest outsider-authored free text from public/upstream documentation pages (e.g., URLs/articles) into the agent’s LLM context for synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata