Skip to content

feat: add OWASP Agent Memory Guard to community security skills#666

Open
vgudur-dev wants to merge 1 commit into
VoltAgent:mainfrom
vgudur-dev:add-amg
Open

feat: add OWASP Agent Memory Guard to community security skills#666
vgudur-dev wants to merge 1 commit into
VoltAgent:mainfrom
vgudur-dev:add-amg

Conversation

@vgudur-dev

Copy link
Copy Markdown

What this adds

Adds OWASP Agent Memory Guard to the community skills section, alongside other security-focused skills (clawsec, vibesec).

What it does

Agent Memory Guard provides runtime defense against memory poisoning attacks (OWASP ASI06) in AI agent memory stores. It detects:

  • Prompt injection persistence
  • Instruction hijacking via memory
  • Cross-agent contamination

Integrations

Works with Mem0, Zep, ChromaDB, LangChain, and CrewAI.

Details

  • OWASP project under the Agentic Security Initiatives
  • pip install agent-memory-guard
  • 200+ daily downloads on PyPI
  • Apache-2.0 license

Adds Agent Memory Guard — runtime defense against memory poisoning
attacks (OWASP ASI06) in AI agent memory stores. Placed alongside
other security community skills (clawsec, vibesec).
@vgudur-dev

Copy link
Copy Markdown
Author

Hi — this adds OWASP Agent Memory Guard to the community security skills section. It's an OWASP Incubator project (5,400+ downloads) providing memory poisoning defense for AI agents. Would appreciate a review!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants