skills/venhdev/skills/url-to-markdown/Gen Agent Trust Hub

url-to-markdown

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from external URLs, which creates an attack surface for indirect prompt injection if an agent subsequently reads the generated Markdown files.
  • Ingestion points: HTML content fetched from user-provided URLs in scripts/converter.js via the fetch API.
  • Boundary markers: Output is delimited with Markdown headers (# Title) and a source footer (**Source:**) in scripts/cli.js to separate extracted content from metadata.
  • Capability inventory: Performs network fetches in scripts/converter.js and writes files to the local filesystem in scripts/cli.js using fs.writeFileSync.
  • Sanitization: Employs @mozilla/readability to isolate main article content and turndown to convert HTML to Markdown, which effectively strips most executable scripts and styles from the final output.
  • [SAFE]: The skill implementation follows secure coding practices, such as using timeouts for network requests, providing a dependency checker that does not automatically execute commands, and using explicit file system paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 08:03 AM
Security Audit — agent-trust-hub — url-to-markdown