youtube-channel
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
stophyCLI and@stophy/clivianpxto fetch data from YouTube. These tools are provided by the skill's author and are used within the scope of the skill's intended functionality. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes external YouTube channel metadata (descriptions, about pages).
- Ingestion points: YouTube channel descriptions and links retrieved via the
stophy channelcommand. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided in the instructions.
- Capability inventory: Shell command execution restricted to
stophyandnpx @stophy/clitools as defined in theallowed-toolsfrontmatter. - Sanitization: No explicit validation or sanitization of the fetched external data is mentioned.
Audit Metadata