stophy-search

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill executes the @stophy/cli package via npx, which fetches the tool from the npm registry. This is a vendor-owned resource used for the skill's primary functionality.\n- [REMOTE_CODE_EXECUTION]: The skill performs remote code execution by running the @stophy/cli package downloaded at runtime.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute CLI commands for interacting with the YouTube search API.\n- [PROMPT_INJECTION]: The skill processes untrusted user search queries by interpolating them into shell commands, creating a potential indirect prompt injection surface.\n
  • Ingestion points: User search queries provided to the --q flag in SKILL.md.\n
  • Boundary markers: The instructions require wrapping the query in double quotes to delimit user input.\n
  • Capability inventory: Subprocess execution via the Bash tool.\n
  • Sanitization: The skill provides explicit instructions to never splice user text outside of the quoted argument to prevent command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 12:02 PM