ux

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow ingests the outsider’s free-text request (query) to decide whether to audit or design, and then produces an output based on that text; it is not shown that it reads any outsider-authored content from external feeds or user-submitted documents besides the prompt itself.