Skills
skills/varlabz/skills/convert-to-markdown/Gen Agent Trust Hub

convert-to-markdown

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts and the uvx tool to perform file and URL conversions. These operations are essential to the skill's purpose.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from remote sources. scripts/mhtml-to-md.py retrieves MHTML content from arbitrary URLs via urllib.request, and scripts/youtube-transcript.py downloads metadata and subtitles from YouTube. These actions are triggered by user input.
  • [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by converting untrusted external content (web pages and video transcripts) into Markdown for agent consumption.
  • Ingestion points: Remote MHTML URLs in scripts/mhtml-to-md.py and YouTube transcripts in scripts/youtube-transcript.py.
  • Boundary markers: The skill does not currently implement specific delimiters or warnings to the agent to ignore instructions found within the converted content.
  • Capability inventory: The skill has capabilities for network retrieval and local file reading.
  • Sanitization: While scripts/youtube-transcript.py includes a clean_vtt function to strip technical metadata from subtitles, it does not sanitize the text content for potential malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 01:42 AM