research-lit
Warn
Audited by Snyk on Mar 15, 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). This skill explicitly performs web searches of public sources (SKILL.md Step 1: "Use WebSearch ... Check arXiv, Semantic Scholar, Google Scholar") and ingests those third-party pages to analyze papers and drive synthesis/next actions, exposing the agent to untrusted external content that could contain indirect prompt injections.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata