paper-reading
Warn
Audited by Snyk on Apr 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The workflow explicitly downloads and ingests papers from arbitrary "Other URL" sources (PDF download or WebFetch for text) in the "PDF Acquisition" section and then uses the Read tool to parse and act on that content, so the agent will fetch and interpret untrusted public web content as part of its routine (SKILL.md "PDF Acquisition" / "Download Flow" / "Read Content").
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata