ml-paper-writing
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow includes “Search literature using web search and APIs” (e.g., Semantic Scholar/CrossRef/arXiv) and may ingest fetched web/API text into the agent’s LLM context, which is outsider-authored free text from public sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata