repuso

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to connect to Repuso via the Membrane CLI and run actions (e.g., "membrane action run ...") to fetch Repuso data — a social-proof platform of user-generated reviews/testimonials — so the agent will ingest and act on untrusted third-party content from Repuso's APIs.