twitter-downloader

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/download_tweet.py executes external commands to check for and run the downloader.
  • Evidence: The script uses subprocess.run and subprocess.Popen to call yt-dlp with arguments like --version and download parameters.
  • Security: Commands are passed as lists (e.g., ['yt-dlp', '-g', url]) rather than strings, which correctly avoids the use of a shell and prevents shell injection vulnerabilities from user-supplied URLs.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external third-party package.
  • Evidence: SKILL.md instructs users to install yt-dlp via pip and links to its official GitHub repository.
  • Context: yt-dlp is a highly reputable, widely-used open-source media downloader.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external URLs, creating a surface for potential indirect instructions embedded in third-party content.
  • Ingestion points: The url argument in scripts/download_tweet.py accepts external X/Twitter post links.
  • Boundary markers: The skill does not use specific LLM boundary markers for the URL content, but the data is passed to a specialized CLI tool rather than back into an LLM prompt.
  • Capability inventory: The skill has file-system write access and the ability to execute the yt-dlp command.
  • Sanitization: The script implements regex validation ((x\.com|twitter\.com)/\w+/status/\d+) to ensure input URLs conform to expected Twitter post formats before processing.
  • [METADATA_POISONING]: There is a minor inconsistency in the skill's documentation regarding its dependencies.
  • Evidence: The title and description in SKILL.md refer to a tool named twmd, while the usage instructions, dependencies, and implementation script use yt-dlp.
  • Assessment: This appears to be a benign documentation error or an artifact of a tool change during development, posing no security risk to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 11:00 AM