lmstudio-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to curl and read responses from arbitrary remote LM Studio endpoints (e.g., "curl -fsS http://HOST:PORT/v1/models" and the /v1/chat/completions smoke test), meaning the agent will ingest untrusted third-party server responses and use them to choose models and drive downstream actions.