graphic-design

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive review of the skill's instructions and reference files found no evidence of malicious intent or dangerous capabilities.
  • [PROMPT_INJECTION]: The instructions are focused on design principles (WCAG, Gestalt, etc.) and do not contain patterns aimed at overriding agent behavior or bypassing safety filters.
  • [DATA_EXFILTRATION]: No sensitive file paths (e.g., .ssh, .env) are accessed, and there are no commands that initiate network connections to exfiltrate data.
  • [REMOTE_CODE_EXECUTION]: The skill does not download external scripts, install third-party packages, or use any dynamic execution patterns.
  • [NO_CODE]: The skill is entirely composed of markdown files providing instructions and a knowledge base, with no scripts, binaries, or executable content present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 10:07 PM
Security Audit — agent-trust-hub — graphic-design