glare-define-user-needs

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

• Third-party content exposure detected (high risk: 0.80). The skill's Playbook (reference.md "Inputs" table) explicitly lists "Forum Discussions" (text threads, comments) and similar user-generated sources as inputs the agent should review and use to drive the user-needs analysis, meaning it ingests untrusted public content that can materially influence decisions and next actions.