code-review-uncommitted

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOWCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill executes standard git commands including 'git diff', 'git diff --cached', and 'git status --short' to gather change information. These are read-only operations necessary for the skill's functionality.
  • PROMPT_INJECTION (LOW): This skill is vulnerable to Indirect Prompt Injection (Category 8) because it ingests untrusted data from git diffs and project files like 'CLAUDE.md' or 'AGENTS.md'. A malicious user or file could embed instructions to manipulate the subagent reviews. However, since the skill's capabilities are restricted to text-based reporting and do not include file-writing or network operations, the risk is categorized as low.
  • DATA_EXPOSURE (INFO): The skill reads local project files and the global user configuration at '~/.claude/CLAUDE.md'. While this involves accessing sensitive configuration data, it is localized within the user's environment and no external exfiltration patterns were detected.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 07:07 AM