spot-people-posting-about-specific-things

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md) explicitly calls the OpenFunnel API (e.g., POST /api/v1/signal/... and the deploy social-listening-agent endpoint) to scan and return social media posts — untrusted, user-generated third-party content that the agent must read and that influences deployment and follow-up actions.