basecamp

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md instructs the agent to use Membrane to connect to Basecamp and run actions like "list-messages", "get-message", and "list-comments", which fetch user-generated content from Basecamp message boards and to-dos (third-party, untrusted content) that the agent is expected to read and could influence subsequent actions.