nulab

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to run Membrane actions and proxy arbitrary requests (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") against the Nulab API, which returns third‑party/user-generated content (issues, comments, etc.) that the agent is expected to read and could influence subsequent decisions or actions.