youtube-channel
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
stophy channel) using user-provided channel URLs or handles. There is a risk of command injection if the agent interpolates unsanitized user input directly into the shell command string. - [EXTERNAL_DOWNLOADS]: The skill uses
npx @stophy/cli, which involves downloading and executing a package from the npm registry. This package is provided by the skill author ('stophy'). - [PROMPT_INJECTION]: The skill retrieves content from YouTube (e.g., channel descriptions, about pages, video titles). This external data is untrusted and could potentially contain malicious instructions designed to influence the agent's logic once processed.
- Ingestion points: YouTube channel data (about page, video metadata, links) via
stophy channelexecution. - Boundary markers: None defined in the instructions to separate fetched content from instructions.
- Capability inventory: Execute shell commands via
Bashtool (stophy CLI). - Sanitization: No sanitization or validation of the fetched YouTube content is described; the skill treats all metadata as legitimate data.
Audit Metadata