user-advocate

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Design and Purpose: The skill is a set of behavioral instructions (a "lens") intended to help AI agents simulate the perspective of a user advocate. It focuses on questioning the desirability and livability of features being developed.
  • No Executable Code: The skill consists only of a markdown file (SKILL.md) with instructions and metadata. It does not include scripts, binaries, or commands that would be executed on a host system.
  • Metadata and Shortcuts: The metadata (name, version, shortcut) and auto-activation keywords are consistent with the stated purpose of the skill. There is no evidence of metadata poisoning or deceptive instructions.
  • External Resources: The skill does not reference external URLs, download remote content, or specify third-party dependencies. It operates within the context provided by the user.
  • Data Handling: There are no instructions that attempt to access sensitive files (e.g., credentials, SSH keys) or exfiltrate data to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:27 AM
Security Audit — agent-trust-hub — user-advocate