insided

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md requires connecting to InSided via the Membrane CLI and using actions (e.g., action list/run) to fetch and interact with Articles, Posts, Comments and User content from InSided (a public, user-generated community), which the agent is expected to read and act on as part of its workflow, exposing it to potential indirect prompt injection.