minimal-diff-formatter

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions and code for formatting output as unified diffs to save tokens and improve readability. It does not perform any network operations, access sensitive files, or execute untrusted code.
  • [SAFE]: The included Python implementation uses only standard library modules (difflib, pathlib) for text processing and does not involve dynamic execution of external input.
  • [PROMPT_INJECTION]: The skill contains an operational directive for agents to use a specific output format. This is a benign formatting constraint and does not attempt to bypass safety guidelines, extract system prompts, or override core agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 12:21 AM