gloww

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md instructs using Membrane to proxy requests to the Gloww API (e.g., "membrane request CONNECTION_ID /path/to/endpoint") and lists user-generated content types like "Community Post", "Comment", "Message", and "Chat Room", indicating the agent will fetch and read untrusted third-party user content from Gloww that could influence subsequent actions.