ui-review

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md Step 2 and scripts/capture.py) explicitly navigates to and captures screenshots of arbitrary developer-provided DEV_URLs and optional public Figma URLs, and scripts/analyze.py then loads those images and metadata into a payload that is fed to the model for analysis, meaning untrusted third‑party content is fetched and directly influences the agent's review decisions.