youtube-playlist
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @stophy/clito fetch and execute a package from the NPM registry. This package is an official tool from the skill's author ('stophy') used to provide the playlist retrieval functionality. - [COMMAND_EXECUTION]: The skill leverages shell commands via the
stophyCLI ornpxto perform network requests to YouTube. The commands are scoped to the intended purpose of fetching playlist data. - [PROMPT_INJECTION]: The skill processes external data from YouTube (titles, descriptions), which creates an indirect prompt injection surface where instructions hidden in video metadata could attempt to influence the agent's behavior.
- Ingestion points: YouTube metadata retrieved via the
stophy playlistcommand inSKILL.md. - Boundary markers: None provided in the command instructions or output guidance.
- Capability inventory:
Bashtool access used for CLI execution. - Sanitization: No specific sanitization or escaping of the retrieved metadata is mentioned in the workflow instructions.
Audit Metadata