mkt-root-cause

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

• Third-party content exposure detected (high risk: 1.00). The skill's "Before Starting" instructions explicitly tell the agent to "Use WebSearch for publicly available evidence" (e.g., competitor launch dates, industry trends), meaning the agent will fetch and read open/public third-party web content that can influence hypothesis verdicts and next actions.