skills/donngi/skills/commit/Gen Agent Trust Hub

commit

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is susceptible to indirect prompt injection from the codebase it analyzes.
  • Ingestion points: git diff, git log, and git diff --staged are used to read file content and history (SKILL.md).
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded prompts within the diff output.
  • Capability inventory: The skill has the ability to execute git add and git commit via the Bash tool.
  • Sanitization: Absent; the agent processes the raw output of git commands to generate commit messages and determine logical splits.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM