auto-git-commiter

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Git commands such as git add, git commit, and git push to automate version control operations.- [DATA_EXFILTRATION]: The skill transmits local workspace content to remote Git repositories. This behavior is documented as the core functionality and targets well-known services like GitHub.- [PROMPT_INJECTION]: The skill reads modified workspace files to generate commit messages, creating a surface for indirect prompt injection. \n
  • Ingestion points: Reads modified file content and paths via git.status() and status filtering.\n
  • Boundary markers: No delimiters or instructions are used to prevent the agent from obeying instructions embedded in the analyzed files.\n
  • Capability inventory: Includes the ability to commit changes and push data to remote network locations.\n
  • Sanitization: No evidence of sanitization or validation for content processed during commit message generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:09 AM
Security Audit — agent-trust-hub — auto-git-commiter