plain-english

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill manages a set of persistent style instructions within the user's global configuration file (~/.claude/CLAUDE.md). This intended behavior modification is implemented with high transparency, utilizing clear delimited blocks and requiring explicit user consent. While the skill processes user input in its rewrite mode, this is a standard transformation task with no signs of malicious interpolation.
  • [COMMAND_EXECUTION]: Executes a bundled Python script (scripts/check-swaps.py) to verify text against a predefined list of banned terms. This script operates entirely locally using standard Python libraries and does not perform network operations or access sensitive system data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:19 PM
Security Audit — agent-trust-hub — plain-english