voice-editor

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown instructions and reference files. It does not contain scripts, binaries, or automated installation steps.
  • [SAFE]: No network operations, data exfiltration, or credential access patterns were detected. The skill interacts only with local files (like VOICE.md) which is consistent with its stated purpose of editing drafts.
  • [SAFE]: The instructions emphasize user review and the '30-40% Rule', encouraging human oversight rather than autonomous agent behavior.
  • [SAFE]: The allowed-tools list (Read, Write, Edit, Glob, Grep, AskUserQuestion) is standard for a file-editing agent and is appropriately scoped for the tasks described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 06:16 AM
Security Audit — agent-trust-hub — voice-editor