lm-studio

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs downloading models from public hubs (e.g., "lms get" in SKILL.md Phase 1b) and configuring MCP integrations that can call external servers (references/lms-commands.md — REST API: MCP Integration, example using https://huggingface.co/mcp), meaning it fetches and ingests untrusted third-party content that can materially influence model/tool behavior.