uscreen

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to connect to Uscreen via the Membrane CLI and to list/run actions that read/manage Uscreen resources (e.g., Blog Post, Comment, Page, User), which are third‑party, potentially user‑generated contents the agent will ingest and can influence subsequent actions.