web-design-reviewer
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from potentially untrusted external websites and possesses the authority to modify local source code.
- Ingestion points: The agent retrieves the DOM structure and visual screenshots from target URLs (SKILL.md, Section 2.1).
- Boundary markers: None. There are no instructions to the agent to treat website content as untrusted data or to use delimiters to prevent instruction injection.
- Capability inventory: The skill requires 'File Read/Write' for code editing and 'Web Page Navigation' for accessing websites (SKILL.md, Required Capabilities).
- Sanitization: None. There is no evidence of sanitization or safety validation of the data retrieved from external URLs before it influences file-system operations.
- [EXTERNAL_DOWNLOADS]: The skill documentation recommends using
npx -y @playwright/mcp@latestfor browser automation. This command fetches and executes the Playwright MCP server from Microsoft's official package registry. This is a reference to a well-known service and is documented here for completeness.
Audit Metadata