find-papers
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The
/find-papers "<prompt>"runtime workflow instructs the agent to query multiple outsider-authored sources (e.g., arXiv, Google Scholar, Semantic Scholar, PubMed Central) and to “read the full abstract and metadata of every candidate paper retrieved” into the LLM context, meaning third-party paper text is ingested after an outsider supplies a search prompt.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata