skills/steveclarke/dotfiles/clarify/Gen Agent Trust Hub

clarify

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for UX writing and copy improvement. No executable code or shell commands are present.
  • [SAFE]: No network operations, file system access, or credential usage were detected.
  • [SAFE]: The skill references an internal command '/impeccable' to gather context, which is a standard instructional pattern for this agent platform.
  • [SAFE]: While the skill processes user-supplied interface text via the '[target]' argument, it lacks the tools or capabilities (like file writes or network access) to perform harmful actions if malicious instructions were embedded in the target text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:51 PM
Security Audit — agent-trust-hub — clarify