strategic-insights-prioritizer

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s workflow ingests “research from all relevant sources” and “stakeholder input” (free-form text from users/other parties) via the runtime input provided to the agent, which can include outsider-authored comments/messages/issues; this text is then used to extract opportunities and populate the LLM context for scoring and ranking.