youtube-for-ai

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external YouTube sources, creating an attack surface for indirect prompt injection.
  • Ingestion points: YouTube transcripts, comments, and live chat retrieved via CLI commands in SKILL.md.
  • Boundary markers: The instructions do not define delimiters to separate untrusted data from the agent prompt.
  • Capability inventory: The agent has access to the Bash tool to execute system commands.
  • Sanitization: No sanitization or filtering of the retrieved YouTube content is specified.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx @stophy/cli to execute functions, which downloads the package from the npm registry if not locally available. This resource belongs to the author's vendor namespace.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:24 PM