search-first
Warn
Audited by Snyk on Apr 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's researcher workflow explicitly instructs the agent to search and ingest content from public sources like npm/PyPI, GitHub and the open web (see "Search: npm/PyPI, MCP servers, Claude Code skills, GitHub" and the Full Mode task in SKILL.md), and those third-party findings are used to decide whether to adopt/extend/build and thus can change subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata