product-intelligence

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

• Third-party content exposure detected (high risk: 1.00). The skill's pipeline explicitly instructs agents to "monitor competitor changelogs, release notes, Product Hunt launches" and to "collect signals" from user-generated sources like app reviews and community posts (SKILL.md Steps 1–2), meaning the agent will fetch and ingest untrusted public web and social/forum content that can influence decisions.