writing-rules

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a collection of Markdown-based instruction files and reference guides. It serves as a stylistic framework for an AI agent to produce well-formatted Japanese content.
  • [SAFE]: No executable code (Python, JavaScript, or shell scripts) is included in the provided files. The skill operates entirely through natural language instructions that govern the agent's behavior during text generation.
  • [SAFE]: There is no evidence of prompt injection, data exfiltration, or obfuscation. All external links point to established documentation standards such as Semantic Versioning (semver.org) and Keep a Changelog.
  • [SAFE]: While the instructions mention other skills (e.g., check-terms, yomiyasu, session-status), these are treated as modular tools within the agent's environment, and the current skill does not perform any autonomous network operations or file system manipulations itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 04:53 AM