poteto-mode

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the shell tool (or run in Claude Code) to execute development commands, manage git worktrees, and run project-specific scripts. These are standard development activities within the context of an engineering agent.
  • [COMMAND_EXECUTION]: Several bundled scripts (e.g., scripts/watch-pr/watch-pr, scripts/orch/orch.ts, scripts/worktree-audit.sh) are designed to be executed via the agent's shell to automate GitHub PR monitoring, project orchestration, and disk cleanup. These scripts primarily interact with local files and the official GitHub CLI (gh).
  • [NO_CODE]: While the skill contains TypeScript and Shell scripts, these are developer tools for the agent's own use (orchestration, PR watching, auditing) rather than application code meant for deployment. No suspicious external dependencies or remote code execution patterns were detected; dependencies in package.json are limited to standard libraries like commander.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 11:12 PM
Security Audit — agent-trust-hub — poteto-mode