commit-messages

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local build and quality assurance tools. Specifically, it runs make format and make lint to ensure code quality before generating a commit. It also uses cat or sed to preview generated files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of git diffs and repository status through the sanctum:git-workspace-review dependency.
  • Ingestion points: The skill ingests the output of sanctum:git-workspace-review (repository path, status, and diffs) to generate commit descriptions.
  • Boundary markers: No specific delimiters or 'ignore instructions' markers are defined for the diff content processed by the agent.
  • Capability inventory: The skill can execute shell commands (make, cat, sed) and write files to the local file system (Write, TodoWrite).
  • Sanitization: There is no explicit sanitization or filtering of the content found within git diffs before it is used for generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:51 PM