Article Writer
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: 0.90). The skill explicitly ingests and analyzes open, third-party content—e.g., scripts/scholar_search.py (searches Google Scholar/Semantic Scholar), python scripts/pdf_reader.py (reads arbitrary PDFs), and /article-writer:add-code which accepts GitHub repo URLs—so the agent will read and interpret untrusted, user-generated web content as part of its workflow.
Audit Metadata