enterprise-ux-process

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow includes collecting and ingesting outsider-authored free text such as “stakeholder-interview transcripts” and “user-research report” content from non-operating-user participants (Phases 2 and 4), which is then fed into the agent’s LLM context for synthesis and outputs.