git-commit-writer

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external content (git diffs) as its primary input. This establishes a surface for indirect prompt injection where malicious instructions could be embedded in a diff to influence the agent. The risk is assessed as low because the skill lacks access to the network, filesystem, or shell, and it instructs the agent to treat the input data strictly as data, not instructions.\n- [SAFE]: The skill provides an installation command that fetches its own source code from the author's official GitHub repository (github.com/theneoai/...). This is a legitimate and safe distribution method for the vendor's own assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 09:44 AM
Security Audit — agent-trust-hub — git-commit-writer