Agent 与自动化 4.0 · 优秀 2026-09-19 · GitHub

OWASP Agent Memory Guard:针对 agent 记忆中毒的运行时防御项目上线

OWASP Incubator 项目 Agent Memory Guard 以防御转化为主要定位:在上下文重置之后也能拦住记忆中毒,是运行时防御而非静态扫描现有探测器覆盖提示注入凭证/PII 泄露保护键修改存储异常与自增强循环;同时提供 vector-store 保护与实时仪表盘在 PyPI 上 agent-memory-guard 与 langchain-agent-memory-guard 两个包可用该项目与本地 agent 路径直接相关:Obsidian 记忆底层mem0 / 自研 store 都需要一份上下文重置后仍然拦住中毒的运行时护栏,而不仅仅是抽取阶段的检索过滤

打开原文回到归档

OWASP Agent Memory Guard:针对 agent 记忆中毒的运行时防御项目上线

  • ID: 2148ebde
  • 原文链接: https://github.com/OWASP/www-project-agent-memory-guard
  • 作者: OWASP Foundation (Incubator)
  • 日期: 2026-09-19
  • 分类: agents
  • 来源类型: github
  • 标签: agent-security, memory-poisoning, owasp, defense, mcp
  • 质量评分: 4/5
  • 抓取时间: 2026-09-19T22:35:00Z

中文导读

OWASP Incubator 项目 Agent Memory Guard 以防御转化为主要定位:“在上下文重置之后也能拦住记忆中毒”,是运行时防御而非静态扫描。现有探测器覆盖提示注入、凭证/PII 泄露、保护键修改、存储异常与自增强循环;同时提供 vector-store 保护与实时仪表盘。在 PyPI 上 agent-memory-guard 与 langchain-agent-memory-guard 两个包可用。该项目与本地 agent 路径直接相关:Obsidian 记忆底层、mem0 / 自研 store 都需要一份“上下文重置后仍然拦住中毒”的运行时护栏,而不仅仅是抽取阶段的检索过滤。

为什么值得关注

OWASP Agent Memory Guard 上线:运行时拦住上下文重置后的记忆中毒,PyPI 双包可用

关键信息

English Summary

OWASP Incubator project Agent Memory Guard is positioned as runtime defense that catches memory poisoning even after a context reset — not a static scanner. Current detectors cover prompt injection, secret/PII leakage, protected-key modifications, size anomalies, and self-reinforcement loops; the project also ships vector-store protection and a real-time dashboard. Both agent-memory-guard and langchain-agent-memory-guard are available on PyPI. The relevance to local-agent paths is direct: Obsidian-backed memory, mem0, and homegrown stores all need a runtime guard that survives context resets rather than only a one-shot retrieval filter.