youtube-for-ai

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx @stophy/cli to download and run the command-line interface from the npm registry. This is a standard and expected method for using the vendor's tool.
  • [COMMAND_EXECUTION]: The skill functions by executing stophy CLI commands through a Bash interface. These commands facilitate authentication and data retrieval from YouTube (search, transcripts, comments, etc.).
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests untrusted data from external sources (YouTube transcripts, comments, and live chat).
  • Ingestion points: Content is retrieved using commands like stophy video transcript and stophy video comments in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters to isolate external content from the agent's internal logic.
  • Capability inventory: The skill uses the Bash tool to execute CLI operations.
  • Sanitization: There are no documented steps for sanitizing or filtering the retrieved YouTube data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 02:04 AM