deep-research
Warn
Audited by Snyk on Jun 19, 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). The skill’s runtime workflow (“Iterative Search” over at least 10 search rounds) necessarily fetches and reads public web/search results as readable text, which is outsider-authored content that can be injected into the LLM context via retrieved pages/snippets.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata