explore-directions

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [SAFE]: The skill does not contain any malicious code, hidden instructions, or obfuscated payloads. Its behavior is consistent with its stated purpose of assisting in UI design exploration.
  • [COMMAND_EXECUTION]: The skill utilizes platform-specific syntax (!) to execute benign shell commands at load time, such as git branch and git status. These commands provide the agent with relevant project context without exposing sensitive information or accepting unsanitized user input.
  • [DATA_EXFILTRATION]: The instructions for generating HTML mockups include a mandatory security requirement to emit a restrictive Content Security Policy (CSP) meta tag (default-src 'none'; style-src 'unsafe-inline'; script-src 'unsafe-inline'; img-src data:). This is a strong defensive measure that prevents the generated mockup from making external network requests or exfiltrating data via remote fetches.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:55 PM
Security Audit — agent-trust-hub — explore-directions