cmd-pr-test-plan

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard CLI tools (git, gh, grep) to inspect the current repository state and history. These commands are restricted to local analysis of the codebase.
  • [COMMAND_EXECUTION]: The skill automatically detects project tooling by scanning for common configuration files like Makefile, pyproject.toml, and package.json. This allows it to reference project-specific commands rather than generic ones.
  • [DATA_EXFILTRATION]: There are no network operations or external data transfer patterns detected. The disable-model-invocation: true flag further indicates the skill's intent for local command generation without unnecessary LLM call-backs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 05:11 PM