design-md-creator

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for visual design extraction and recreation, with no evidence of malicious intent or hidden code.
  • [DATA_EXFILTRATION]: The instructions explicitly direct the agent to avoid capturing or reproducing sensitive elements like authentication, payments, or private APIs from reference websites, which helps prevent accidental data exposure.
  • [COMMAND_EXECUTION]: The skill utilizes standard environment tools to open browser windows or start local preview servers, which are strictly scoped to the local display of generated HTML artifacts.
  • [PROMPT_INJECTION]: While the skill ingests content from external URLs, which represents a potential indirect injection surface, it mitigates this by focusing on visual metadata extraction and explicitly recommending against the use of complex or untrusted JavaScript in the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 10:23 PM
Security Audit — agent-trust-hub — design-md-creator