search-first
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s “researcher agent” workflow instructs the agent to search across external sources (npm/PyPI, MCP servers, and GitHub/Web) and then read their resulting content for evaluation/return, which can include outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata