git-commit-writer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the bash tool to run read-only git commands (status, diff, log) to gather context from the local repository.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted data from the repository's staged changes and history. 1. Ingestion points: staged changes via git diff --staged and commit history via git log. 2. Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the instructions. 3. Capability inventory: Ability to execute git commit via bash (which the skill is instructed to do only after user approval). 4. Sanitization: No explicit sanitization of the read content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 08:22 AM
Security Audit — agent-trust-hub — git-commit-writer