conventional-commits

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • SAFE (SAFE): No malicious patterns detected. The skill consists entirely of text-based instructions for the agent.
  • Indirect Prompt Injection (INFO): The skill processes untrusted data from git diffs. While this allows for potential prompt injection, the lack of side-effect capabilities (no write, network, or execute) makes this an information-only finding.
  • Data Exposure (INFO): The skill reads staged code changes to provide summaries, which is a functional requirement but involves processing repository content.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:36 AM