minecraft-modding-workbench

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to resolve and inspect external artifacts and mod JARs (e.g., inspect-minecraft, analyze-mod, analyze-symbol, and the MCP recipes that resolve artifacts or read Gradle caches / dependency jars), which are untrusted, user-authored third‑party files the agent is expected to read and that can materially affect subsequent tool use and decisions.