openevidence
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: 0.70). This skill directly fetches and ingests content from the public OpenEvidence site (scripts/oe.py uses GET/POST to /api/article and /api/article/list and downloads article text/figures, and SKILL.md documents the ask/article flows), so untrusted third‑party article content and linked resources are read and returned for the agent to use and could therefore inject instructions that influence subsequent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata