markdown-new
Warn
Audited by Snyk on Feb 19, 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). This skill accepts arbitrary public http/https URLs (validated and passed to markdown.new) and fetches their content via the POST/GET API (see scripts/markdown_new_fetch.py and SKILL.md), returning Markdown intended for LLM summarization/RAG/extraction — meaning untrusted third‑party page content can be ingested and influence downstream agent decisions.
Audit Metadata