skills/bulls-cows/skills/yy-commit/Gen Agent Trust Hub

yy-commit

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Git CLI commands (git status, git diff, git add, git commit) to manage the repository state. These are standard operations for the tool's purpose.
  • [SAFE]: Implements explicit safety checks for sensitive files, instructing the agent to warn the user if credentials, environment variables (.env), or private keys (*.key, *.pem) are detected in the change set.
  • [SAFE]: Enforces a mandatory confirmation step, preventing the agent from autonomously committing code without explicit user approval of the files and the commit message.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the project's source code (via git diff) and history. While this presents a potential injection surface, the risk is mitigated by the fact that the output (a commit message) is reviewed by a human before any execution occurs.
  • [DATA_EXPOSURE]: Reads local file differences and commit history to generate summaries. This information is restricted to the local context and is not transmitted to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 06:34 AM
Security Audit — agent-trust-hub — yy-commit