h3-prompt-writing

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and contains no executable code or scripts. It operates by reading local reference files (references/base-en.txt and references/ref-en.txt) to guide the agent in formatting prompt outputs.
  • [SAFE]: No network-based threat vectors were identified. The skill does not use curl, wget, or any other tool to fetch remote content or exfiltrate data.
  • [SAFE]: The skill lacks dangerous capabilities such as file system writes, command execution, or environment variable access. It strictly focuses on prompt engineering and structure.
  • [SAFE]: There are no signs of obfuscation, hidden URLs, or malicious prompt injection patterns. The instructions are transparent and aligned with the described purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 02:19 PM
Security Audit — agent-trust-hub — h3-prompt-writing