literature-triangulation
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s workflow requires searching and reading primary sources from the public web (e.g., arXiv/venue pages, code repos/README files, benchmark/dataset papers), and those fetched outsider-authored documents’ readable text would be ingested into the agent’s LLM context during synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata