Skip to content
Cisco AI Defense logo
CiscoAI Security

DefenseClaw

DefenseClaw

Enterprise governance for AI agents — scan, enforce, and audit every skill, MCP server, and plugin before it runs.

DefenseClaw is the enterprise governance layer for OpenClaw. It sits between your AI agents and the infrastructure they run on, enforcing a simple principle: nothing runs until it's scanned, and anything dangerous is blocked automatically.

View on GitHub | Join Discord | Cisco AI Defense


How It Works

1. Install — Build from source or use the curl installer. Run defenseclaw init to create the config directory, SQLite audit database, and install scanner dependencies.

2. Configure — Set up scanners (setup skill-scanner, setup mcp-scanner), the LLM guardrail (setup guardrail), and optionally Splunk integration (setup splunk). Or use --enable-guardrail during init for a one-step setup.

3. Protect — Every skill install, MCP connection, and tool call passes through the admission gate: block list, allow list, scan, enforce. Findings are logged to the audit store and optionally forwarded to Splunk or any OTLP-compatible backend.


What It Protects

TargetScannerWhat it detects
SkillsCisco skill-scannerPrompt injection, data exfiltration, command injection, obfuscated code, supply chain risks
MCP ServersCisco mcp-scannerHidden instructions, malicious tool descriptions, suspicious endpoints
PluginsBuilt-in + external scannerBehavioral analysis, YARA patterns, LLM semantic analysis
CodeCodeGuard / ClawShieldHardcoded secrets, dangerous exec patterns, PII exposure, injection vulnerabilities
Tool CallsGateway sidecar (real-time)Credential leaks, destructive operations, data exfiltration in tool arguments
LLM TrafficLiteLLM guardrailPrompt injection, secret leakage, exfiltration patterns in prompts and responses

Admission Gate

Every skill, MCP server, and plugin passes through this flow:

  1. Block list? — If blocked, reject immediately. Log and alert.
  2. Allow list? — If allowed, skip scanning. Install, log, and inventory.
  3. Scan — Run configured scanners.
  4. Clean? — Install and log.
  5. High/Critical? — Reject, quarantine, log, and alert.
  6. Medium/Low? — Install with warning, log, and alert.

Documentation

GuideDescription
InstallationPrerequisites, install methods, init and setup walkthrough
FeaturesComplete list of implemented capabilities
Quick StartGet running in 5 minutes
CLI ReferenceAll commands, flags, and examples
ExamplesReal-world scenarios, OPA policy authoring, OTEL configuration
OpenClaw PluginAutomatic security layer inside OpenClaw
FAQCommon questions and answers

For technical deep-dives, see the Architecture, API Reference, Config Files, and OpenTelemetry Spec in the repository.


License

Apache 2.0 — See LICENSE for details.