wikipedia-human-style-writing

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • Stylistic Reference Implementation: The skill utilizes a reference guide (references/ai-writing-tells.md) to identify and correct common linguistic patterns associated with large language models. This implementation is purely instructional and does not involve executable code or dynamic script generation.
  • Trusted External References: The skill links to Wikipedia's public community guide on AI writing styles. This is a well-known, reputable source used to inform the skill's logic, and its inclusion is consistent with the primary function of assisting with prose neutrality and quality.
  • Limited Capability Surface: Although the skill is designed to process user-provided drafts, it does not request or use any tools that interact with the file system, network, or operating system. The absence of high-privilege capabilities significantly limits the potential impact of processing untrusted content, as the agent's output is restricted to revised text and stylistic reviews.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:32 PM
Security Audit — agent-trust-hub — wikipedia-human-style-writing