science-editor
Warn
Audited by Snyk on Feb 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: 1.00). The skill's "Research and actualisation" section explicitly requires using the Browser tool to visit and ingest content from open/public sources (e.g., Google Images, YouTube, ArXiv, news sites like Wired/The Atlantic), so the agent will fetch and read untrusted third‑party web and user-generated content as part of its workflow.
Audit Metadata