ask-commit-assistance

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes local file content to generate reviews and commit messages, which is a surface for indirect prompt injection. This is considered safe as the skill requires manual user intervention for any state-changing commands. \n
  • Ingestion points: Local files identified via git status and git diff are read during the workflow. \n
  • Boundary markers: No explicit markers or instructions to ignore embedded commands are present in the workflow. \n
  • Capability inventory: The skill can stage files via git add and generate shell commands for the user to execute. \n
  • Sanitization: There is no explicit sanitization or filtering of the content read from files before processing. \n- [COMMAND_EXECUTION]: The skill uses local Git CLI tools (git status, git add) as part of its core utility. It avoids automated commits, presenting them instead for the user to review and run manually.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 03:04 AM