literature-review
Warn
Audited by Snyk on May 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: 1.00). The SKILL.md explicitly requires searching and ingesting third‑party sources ("Search across multiple source types" — e.g., "Semantic Scholar", "Web search", "Videos", "Wikipedia / Scholarpedia"), so the agent will fetch and interpret public/untrusted web content that can materially influence its outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata