memory-poisoning

Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.

Auditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai

Attack taxonomy, toolkit & defenses for persistent-memory poisoning of LLM agents. Author: Krishita Sanjay Choksi.

Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration — benchmark, adaptive red-teaming, and defenses for persistent memory attacks on LLM agents (arXiv:2605.01970)

Security for AI agents & MCP — map how MCP servers, skills, and memory chain into exposure paths. Toxic-flow detection, cross-surface graph, drift & policy-as-code. Local-only, no telemetry.

ZKP-RA: Zero-Knowledge Proof Reasoning Anchors for mitigating memory poisoning in autonomous agentic DeFi — Groth16 zk-SNARKs, Circom circuits, on-chain Solidity verifier, Python agent guardian. 182ms proofs, 9.7x gas reduction vs zkML.

Agent memory with a recall button - Every memory knows its sources. Recall a bad source, and everything learned from it goes too

Memory defense for AI agents — stops MINJA, AgentPoison, and MemoryGraft attacks. Zero dependencies.

AgentInterdict — runtime enforcement for autonomous AI agents. Trust context. Verify authority. Interdict unsafe action.

MemGuard - eBPF-based real-time memory poisoning detection and alerting for LLM agents (AgentSight overlay)

Agent Memory Integrity: a conformance test suite that measures whether AI agent memory and checkpoint stores notice tampering. Measured on LangGraph, OpenAI Agents SDK, LlamaIndex, CrewAI, OpenClaw, Hermes, Letta, Mem0, Vertex AI Memory Bank and the integrity tools that claim tamper evidence. IETF draft-khandelwal-bmwg-agent-memory-integrity.

See what your AI agent's memory holds, what changed, and put it back. Local-first and agent-neutral. Alpha.

Memory integrity for AI agents — Information-flow control against OWASP ASI06 memory & context poisoning.

Stop memory poisoning attacks on your AI agents

AI Security SDK for Agents, LLMs & SLMs

AI Agent Security — Attack payloads, defense references, and research. 52 tests, ~10K lines. A learning-oriented shooting range, not a product.

Owned security intelligence for AI agents - four screening tiers between what your agents learn and what they do. YC Own Your Intelligence hackathon.

This repository documents AI Recommendation Poisoning — a real-world attack technique discovered by Microsoft's Defender Security Research Team (February 2026) where adversaries silently inject persistent instructions into AI assistant memory through carefully crafted URLs.

Agentic AI Request Forgery (AARF) – New vulnerability class exploiting planner ➝ memory ➝ plugin chaining in MCP Server, MAS, LangChain, and A2A agents. Red Team playbooks, threat models, OWASP Top 10 proposal.