canvas-design

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within its declared scope of artistic design. No evidence was found of sensitive file access, credential harvesting, or unauthorized command execution.- [PROMPT_INJECTION]: The instructions include a technique instructing the agent to act as if a user has already requested higher quality ('The user ALREADY said...'). This is used as a behavioral conditioning mechanism to ensure high-fidelity output and does not attempt to bypass safety filters or manipulate system prompts.- [EXTERNAL_DOWNLOADS]: The skill references font acquisition but focuses on a local directory for assets. The included license files contain standard links to official font projects on GitHub and licensing documentation, which are well-known and safe sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 01:48 PM
Security Audit — agent-trust-hub — canvas-design