skills/tukaelu/agent-skills/committer/Gen Agent Trust Hub

committer

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git commands to analyze repository state and create commits. It specifically uses git status, git diff, git log, git add, and git commit to manage the local development workflow.
  • [PROMPT_INJECTION]: Indirect prompt injection surface exists as the skill processes untrusted local file content.
  • Ingestion points: Reads repository files and diffs via git diff and the Read tool in Step 2 to understand change intent.
  • Boundary markers: No specific boundary markers are defined for the ingested file content during processing.
  • Capability inventory: Possesses the ability to execute shell commands via the Bash tool (primarily focused on git * commands) and interact with the user via AskUserQuestion.
  • Sanitization: Implements robust sanitization through mandatory user approval. Step 4 requires the user to review and confirm the proposed commit plan before any write operations occur, and Step 1 and Step 5 include specific confirmations for branch and GPG security settings.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:31 AM