youtube-livechat
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto fetch and run the@stophy/clitool. This is a standard mechanism for executing the vendor's provided utility. - [COMMAND_EXECUTION]: The instructions direct the agent to run the
stophycommand-line interface to retrieve live chat data from YouTube. - [PROMPT_INJECTION]: The skill processes live chat data which is sourced from external, untrusted users. This introduces a risk of indirect prompt injection.
- Ingestion points: Live chat messages fetched via the
stophy video livechatcommand. - Boundary markers: Absent; there are no instructions to the agent on how to isolate chat text from control logic.
- Capability inventory: The skill allows the execution of shell commands through the
stophyCLI andnpx(SKILL.md). - Sanitization: No validation or sanitization of the retrieved chat messages is mentioned.
Audit Metadata