youtube-livechat
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
stophyCLI tool andnpx @stophy/clito retrieve live stream data. These commands are part of the intended functionality provided by the author. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch the@stophy/clipackage. This is an official package associated with the skill's author and is used for its primary function. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes live chat messages from YouTube which are controlled by external users.
- Ingestion points: The agent reads chat data via the
messages[]array returned by thelivechatcommand inSKILL.md. - Boundary markers: The skill lacks explicit instructions or delimiters (e.g., XML tags or clear separators) to help the agent distinguish between chat content and system instructions.
- Capability inventory: The agent has access to the
Bashtool, which is used to execute the data-fetching commands. - Sanitization: There is no evidence of message sanitization or filtering before the content is processed by the AI.
Audit Metadata