pass-the-baton

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to automate issue management, including creating, viewing, and commenting on issues. It also executes a local Node.js script (check-plan.mjs) to verify data integrity during the handoff process.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it retrieves and processes instructions and data from GitHub issue bodies and comments.\n
  • Ingestion points: Content from GitHub issues (github-issue.md).\n
  • Boundary markers: The skill relies on human oversight for verification rather than programmatic boundary markers in data ingestion.\n
  • Capability inventory: GitHub CLI operations, local script execution, and temporary file creation.\n
  • Sanitization: The skill does not explicitly sanitize the remote data before passing it to internal processing scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:52 AM