yt-dlp-downloader

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION] (HIGH): Shell command injection vulnerability in scripts/download.sh. The script captures arbitrary user-supplied arguments in $EXTRA_ARGS and executes them unquoted within a bash shell. This allows for the execution of arbitrary commands or the use of dangerous yt-dlp flags like --exec.
  • [PROMPT_INJECTION] (HIGH): Vulnerable to Indirect Prompt Injection (Category 8). * Ingestion points: The skill ingests untrusted metadata (titles, descriptions) from external URLs via yt-dlp. * Boundary markers: None present in the prompt instructions or script. * Capability inventory: Shell execution (yt-dlp) and file system write access (~/Downloads). * Sanitization: No sanitization is performed on the data retrieved from external sources before it is returned to the agent's context.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): Relies on the yt-dlp external utility and performs network requests to thousands of third-party domains to fetch media content.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 10:15 PM