interface-auditor

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md Step 3 explicitly calls the external API endpoints (https://uxuiprinciples.com/api/v1/smells and /lookup) and requires ingesting the returned "recipe_steps" and related fields into the agent's decision/output workflow, so it fetches public third‑party content that can materially influence actions and could carry injected instructions.