product-hunt

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

• Third-party content exposure detected (high risk: 0.80). The skill integrates with Product Hunt via the Membrane CLI and explicitly fetches/interacts with Product Hunt "Posts" and "Comments" (user-generated public content) as part of its required workflow (SKILL.md), so untrusted third-party content would be read and could influence agent actions.