skills/softspark/ai-toolkit/commit/Gen Agent Trust Hub

commit

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to manage git commits and perform local repository checks. All scripts and commands are local and align with the stated purpose of the skill.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool and a local Python script (scripts/pre-commit-check.py) to interact with the git repository. These commands (e.g., git diff, git branch) are restricted to reading the repository state and validating staged changes.
  • [DYNAMIC_CONTEXT_INJECTION]: The SKILL.md file uses dynamic injection (!) to provide the agent with the current branch name and a summary of staged changes. These commands are benign and execute within the local project context.
  • [CREDENTIALS_SAFE]: The bundled Python script includes a secret detection feature that uses regular expressions to find potential API keys or tokens in staged changes. This is a defensive security measure intended to prevent data exposure, and the script does not transmit this data externally.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:07 AM
Security Audit — agent-trust-hub — commit