ClawGuard Shield
AI Agent Security Scanner — detect prompt injection, jailbreaks, and tool poisoning in real-time.
Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only
What it can do
- Scan Text: Scan text for prompt injection attacks, jailbreak attempts, and other AI security threats. Detects 204+ attack patterns across 15 languages. Returns findings with severity, confidence, and
- Scan Mcp Config: Scan an MCP server configuration for security vulnerabilities: tool poisoning, permission escalation, data exfiltration vectors, hidden instructions, and prompt injection in tool desc
What data it sees
Do you need an account
No: the server works without sign-in
AI Agent Security Scanner — detect prompt injection, jailbreaks, and tool poisoning in real-time. 204+ attack patterns, 15 languages, EU AI Act compliance-ready. Scan text or MCP server configs for threats.
Server tool list (2)
Raw names from tools/list. Only developers need these.
| scan_text | Scan text for prompt injection attacks, jailbreak attempts, and other AI security threats. Detects 204+ attack patterns across 15 languages. Returns findings with severity, confidence, and remediation advice. |
| scan_mcp_config | Scan an MCP server configuration for security vulnerabilities: tool poisoning, permission escalation, data exfiltration vectors, hidden instructions, and prompt injection in tool descriptions. |