Tag: llm-security

AgentSeal is the open-source security toolkit that scans AI agents for dangerous skills, poisoned MCP configs, and prompt injection vulnerabilities. With 225+ attack probes, real-time monitoring, and offline-first protection for 28 agents, it's the defense layer AI development desperately needs.

Malwoverview is an open-source threat hunting tool aggregating 17+ intelligence sources including VirusTotal, Shodan, and AbuseIPDB. Features LLM-powered AI enrichment, YARA scanning, IOC extraction, and privacy-first design for rapid malware triage.

Crust is an open-source AI agent security gateway that intercepts and blocks dangerous tool calls before execution. With 42 built-in rules, 51 DLP patterns, and zero-config setup, it protects your secrets from prompt injection and exfiltration attacks.

MEDUSA is the AI-first security scanner with 9,600+ detection rules for repo poisoning, MCP attacks, and LLM vulnerabilities. Learn how to scan any GitHub repo in seconds and protect your AI supply chain.

Discover how 0DIN AI Scanner's 179 community probes built on NVIDIA garak help organizations find vulnerabilities before deployment. Complete setup guide, real code examples, and comparison with alternatives included.