skills/a-canary/arc-skills/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard workflow for user-perspective verification and reporting. It includes specific dimensions for testing such as functional correctness, presentation quality, and truthfulness of claims without performing any high-risk operations.
  • [SAFE]: File system interactions are limited to writing QA findings and screenshots to the dedicated .arc/director/qa/ directory. No attempts to access sensitive system files or credentials were detected.
  • [SAFE]: The skill explicitly includes security as a dimension to be checked (auth bypass, data exposure, injection surfaces), which is a defensive and quality-focused instruction.
  • [SAFE]: No obfuscation, remote code execution patterns, or persistence mechanisms are present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:52 PM
Security Audit — agent-trust-hub — qa