sci-html
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's integrated sci-extract workflow explicitly instructs the agent to fetch public paper pages (e.g., "Use web_fetch on the arXiv abstract page, then on the PDF/HTML version" in the SKILL.sci-extract "Step 1: Acquire the paper") and the Heilmeier/Mode 1 extraction modes allow/require web_search/web_fetch for external citations, so the agent will ingest untrusted third‑party web content (arXiv/DOI/public webpages or pasted public text) and use that content to decide extraction routing and produce follow-up actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata