stack-ai

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to call and read responses from the Stack AI API (via "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint" in SKILL.md), which are third‑party endpoints that can return user-generated or external content that the agent is expected to parse and act on, so untrusted content could influence subsequent actions.