Protects AI agents from prompt injection attacks, jailbreak attempts, and common web vulnerabilities by screening untrusted input through semantic LLM analysis and static pattern matching.
Simulates the Deadbugz MCP supply-chain attack for educational and research purposes, demonstrating a 3-call gate evasion where tool descriptions mutate to steal credentials.
Aggregates real-time threat intelligence from multiple sources including Feodo Tracker, URLhaus, CISA KEV, and ThreatFox, with IP/hash reputation checking via VirusTotal, AbuseIPDB, and Shodan for comprehensive security monitoring.
Enables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.