Security●●Solid
Agent Memory Guard – OWASP defense for AI agent memory poisoning
OWASP reference implementation for ASI06 memory poisoning with LangChain and AutoGen integrations.
Solve My ProblemBig Brain
vgudur297
3021d ago
Back to browse
GitHub Repository
OWASP Foundation web repository
49 starsPython
AgentThreatBench – Benchmark for AI Agent Memory Security
by vgudur297·Jun 1, 2026·2 points·0 comments
AI Analysis
●●●BangerBig BrainSolve My Problem
First OWASP-backed security layer for ASI06 memory poisoning in agentic AI.
Strengths
- •Addresses ASI06 Memory Poisoning from OWASP Top 10 for LLM Apps — a new vulnerability class.
- •Runtime interception blocks attacks before they corrupt agent behavior across sessions.
- •Integrations with LangChain, AutoGen, OpenAI Agents SDK mean drop-in adoption.
Weaknesses
- •Agent security category is heating up — competing with emerging frameworks like Guardrails AI.
- •Title says 'Benchmark' but it's a defense library — naming confusion hurts discoverability.
Category
Target Audience
AI/ML engineers building agentic applications
Similar To
Guardrails AI · LLM Guard · Rebuff
Similar Projects
Security●●Solid
AgentArmor – open-source 8-layer security framework for AI agents
Eight-layer defense-in-depth for AI agents when Guardrails AI only handles inputs.
Solve My ProblemShip It
AgastyaTodi
1063mo ago
Security●●●Banger
Crawdad – Runtime security layer for autonomous AI agents
Post-quantum crypto and ZK proofs for AI agent security when the category is still emerging.
Big BrainSolve My Problem
AndrewGS
102mo ago
Security●●●Banger
Raypher–eBPF-based runtime security and hardware identity for AI agents
eBPF kernel hooks enforce agent boundaries at <0.05ms latency; no API polling tax.
Big BrainBold BetWizardry
Kidiga
213mo ago
Security●●●Banger
MVAR – Deterministic sink enforcement for AI agent
IFC + capabilities block prompt injection at execution sinks, not input filters—40yr research applied.
Big BrainWizardry
ShawnC21
113mo ago
Security●●●Banger
Lilith-zero update: fast Rust security for agents
Transport-layer security for MCP agents stops exfiltration unlike prompt-based guardrails.
Solve My ProblemWizardry
gregojaca
201mo ago