design-review

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use external tools (Chrome MCP, Playwright MCP, or playwright-cli) to navigate to and download content from user-provided URLs for analysis. While standard for a web audit skill, this introduces external data into the agent's context.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted content from external websites to perform visual audits. This creates an attack surface where a malicious website could include hidden instructions (e.g., in HTML comments or metadata) to manipulate the agent's behavior during the review process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:49 AM
Security Audit — agent-trust-hub — design-review