lit-review
Warn
Audited by Snyk on May 12, 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 skill explicitly instructs agents to use opencite:opencite to resolve DOIs, download PDFs and convert them to markdown from external sites during "Phase 1: Collection" (see SKILL.md Phase 1 and references/brief-template.md and references/paper-card-schema.md), and those harvested third-party source.md/source.pdf files are then read and cited to drive synthesis and direction-paper decisions, so untrusted public web content is ingested and can materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata