ZugaShield Security Scanner

7-layer AI security scanner for OpenClaw. Blocks prompt injection, SSRF, command injection, data leakage, and memory poisoning across ALL channels (Signal, T...

This package is plausible as a gateway scanner, but take these precautions before installing/activating it: 1) Verify the upstream packages: confirm the npm package and PyPI package authors and the GitHub repository (the plugin contains multiple repository/homepage strings — reconcile them). 2) Inspect the Python package 'zugashield' (zugashield_mcp): examine its code on PyPI or the repository before running pip install; a third-party Python package will run code on your host. 3) Check SKILL.md / README for the prompt-injection phrases flagged by the scanner and review any suspicious lines. 4) Don't set sensitive env vars into the process; the plugin tries to whitelist env vars but allows ZUGASHIELD_* feed URLs — ensure those point to trusted, signed feeds, and enable signature verification if available. 5) Test in an isolated/sandboxed OpenClaw instance first (non-production) to verify behavior and network interactions (outbound connections, feed pulls). 6) Prefer packages from an audited source or a repository you control; if you can't validate the Python package or feed origin, treat this as untrusted code. If you want, I can list the exact repo/homepage strings found and point out where they differ, or help you inspect the zugashield_mcp package source if you provide its PyPI link or code.

Type: OpenClaw Skill Name: zugashield Version: 0.1.1 The OpenClaw AgentSkills skill bundle 'zugashield' is a security scanner designed to protect AI agents from various attacks like prompt injection, SSRF, command injection, and data leakage. The code demonstrates strong security practices, such as whitelisting environment variables passed to child processes (`src/preflight.ts`, `src/shield-client.ts`) to prevent secret leakage, and implementing fail-closed mechanisms, especially for tool execution (`src/hooks/pre-tool-exec.ts`). The `SKILL.md` and `README.md` are purely descriptive and do not contain prompt injection attempts against the agent. Crucially, the `test/integration.test.ts` file includes extensive tests against a wide range of real attack payloads, with the explicit expectation that these attacks *will be blocked*, strongly indicating a security-focused and non-malicious intent. There is no evidence of intentional harmful behavior, data exfiltration, backdoors, or obfuscation.