deep-research
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: 1.00). The skill explicitly uses WebSearch/WebFetch and instructs consulting community resources like GitHub and public forums (Phase 2 "Information Gathering" and "Tools to Use"), so the agent will fetch and read untrusted, user-generated content from the open web as part of its workflow.
Audit Metadata