zig

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs fetching and integrating public third‑party code (e.g., the package manifest example with .url pointing to GitHub and commands like "zig fetch https://github.com/...", the MCP tool "zig_fetch", and zvm/zls install examples using curl/GitHub), so it will ingest untrusted public repository content as part of the agent's workflow.