workflow-pr

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill promotes security best practices by explicitly instructing the agent to scan for hardcoded paths, secrets, API keys, and tokens before committing code (SKILL.md, Section 2).
  • [COMMAND_EXECUTION]: The skill facilitates standard development workflow commands for validation and repository management, including pnpm, npm, mypy, pytest, ruff, and make. It also uses the official GitHub CLI (gh) for PR status monitoring and merging.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and process Pull Request comments, which are external and potentially untrusted inputs.
  • Ingestion points: Feedback is retrieved using gh pr view <number> --comments as described in Phase 2 and the Quick Reference section of SKILL.md.
  • Boundary markers: None present; the instructions direct the agent to read and address every comment.
  • Capability inventory: The skill has the capability to execute shell commands for builds and tests, and to perform repository actions like merging.
  • Sanitization: No specific filtering or sanitization of the external comment content is defined, though this is expected behavior for a PR management tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 05:56 AM
Security Audit — agent-trust-hub — workflow-pr