AI, Spatial & Voice UX

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent/UI to accept and parse external references and URLs and to display inline citations from source documents (see "explicit context injection" mentioning external knowledge 'according to the documentation at [URL]' and the "Source Attribution" section linking to URLs), which implies fetching and interpreting untrusted third‑party web content that could influence agent decisions.