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/clito 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
stophyCLI 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 transcriptandstophy video commentsin 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
Bashtool 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