zig-project

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

• Third-party content exposure detected (high risk: 0.70). The skill includes an LLMClient.complete example that performs HTTP calls to a configurable LiteLLM proxy (base_url) and also documents fetching dependencies from external URLs/GitHub (e.g., build.zig.zon entries and "zig fetch https://github.com/..."), which are open/public third‑party sources the agent would consume and could return untrusted/user‑generated content.