scientific-writing
Warn
Audited by Snyk on Apr 16, 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). This skill explicitly requires using the research-lookup skill to fetch and extract literature and data for outlines ("Every document produced is backed by comprehensive literature search...through the research-lookup skill" and "Use the research-lookup skill to gather relevant literature and data" in the Stage 1/outline workflow), so the agent will ingest open/public third‑party content and act on it as part of its writing workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata