Vext Shield

AI-native security suite for OpenClaw. Scans skills for prompt injection, data exfiltration, cognitive rootkits, semantic worms, and more. Includes static an...

This package is a self-contained on-host security suite that includes a static signature database and adversarial test payloads. The presence of many 'malicious' strings and test scripts is intentional — they are used to detect and validate detections. Before installing: 1) Verify you trust the publisher (Vext Labs) or inspect the source yourself; 2) Ensure your host can provide the required OS-level sandboxing tools (macOS: sandbox-exec; Linux: unshare) because the red-team and sandboxed behavioral tests refuse to run without them; 3) Expect local files to be created under ~/.openclaw/vext-shield/ (reports, logs, firewall-policy, baselines); 4) Review shared/threat_signatures.json and skills/vext-redteam/redteam.py if you want to confirm which payloads are included; 5) If you lack kernel sandboxing or are uncomfortable with adversarial test payloads on your machine, avoid running the red-team behavioral tests and restrict usage to static scan/audit functions. Finally, although the code claims 'zero network requests', you should still audit the code paths that parse decoded payloads and any code that would process user-provided inputs to ensure no accidental outbound network actions occur in your environment.

Type: OpenClaw Skill Name: vext-shield Version: 1.2.0 VEXT Shield is a comprehensive security suite for OpenClaw designed to detect AI-native threats. While the bundle contains malicious code samples (e.g., 'tests/fixtures/exfil_skill/sneaky.py') and adversarial payloads (in 'skills/vext-redteam/redteam.py'), these are explicitly documented in 'allowlist.json' and the README as test fixtures and threat signatures for the scanner. The core logic in 'shared/sandbox_runner.py' demonstrates a high security posture, enforcing OS-level kernel isolation (macOS sandbox-exec or Linux unshare) and stripping sensitive environment variables before executing untrusted code. The suite is defensive in nature and aligns with its stated purpose of providing security auditing, monitoring, and red-teaming capabilities.