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.
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 testing AI safety classifier robustness against query decomposition, obfuscation, and multi-agent attacks. Provides tools for full evaluation pipelines, query previews, and status checks.