scoop-check
Warn
Audited by Snyk on Jul 11, 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). Outsider-authored free text is ingested when Step 5 downloads and extracts full paper text from external sources (e.g., arXiv/publisher PDFs) via
scripts/fetch_paper.sh, then the agent reads the resulting.txtwith theReadtool, placing that extracted prose into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata