product-design-review

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by processing external untrusted data during audits.
  • Ingestion points: Untrusted data is ingested via browser automation (live URLs), codebase inspection, and Figma MCP tools (SKILL.md, Step 1).
  • Boundary markers: The instructions do not define specific delimiters or directives to isolate external content from the agent's core instructions.
  • Capability inventory: The skill utilizes capabilities such as browser automation (Playwright), file system access for code reading, and external API interactions via Figma tools.
  • Sanitization: No sanitization or filtering logic is specified for the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 12:44 AM
Security Audit — agent-trust-hub — product-design-review