website-ui-ux-engineer

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and read public web resources (e.g., "use the web_fetch tool to read the relevant documentation pages" in references/maintenance-and-updates.md and public CMS fetching like "YOUR_CMS_REST_API/posts" in references/stack-headless-cms.md and links in references/official-docs.md), which means it ingests open third‑party (including user-generated CMS) content that the agent is expected to interpret and use to drive implementation decisions.