search-lit
Warn
Audited by Snyk on Oct 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent skill queries external academic APIs (PubMed, Semantic Scholar, CrossRef) for literature searches and citation snowballing, where fetched bibliographic records and metadata contain outsider-authored text (titles, abstracts, and author names) that the agent ingests at runtime via search queries and API responses.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata