ave vs www-project-agent-memory-guard
ave: AVE (Agentic Vulnerability Enumeration) is a behavioral classification standard for agentic AI components, addressing the gap in existing vulnerability standards for AI-specific threats. It provides stable IDs, AIVSS scores, and maps findings to established security frameworks like OWASP MCP and MITRE ATLAS.; www-project-agent-memory-guard: OWASP Agent Memory Guard is a runtime defense solution designed to prevent AI agents from being weaponized through their own memory by detecting and blocking memory poisoning attacks. It provides a robust security layer that intercepts malicious writes to agent memory, ensuring the integrity and safety of AI operations even after context resets.
TL;DR
Scanning agent skill files for prompt injection and other AI-specific vulnerabilities
Reference implementation for OWASP ASI06: Memory Poisoning.
Side-by-Side Comparison
Features
Use Cases
FAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.