← 최신 프로덕트

Open-Source Gateway to Stop Tool-Abusing Prompt Injections

If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools.

archestra.ai 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. OpenSkills

    news.ycombinator.com

    Stop bloating your LLM context with unused instructions

    Hacker News9점

  2. Find prompts that jailbreak your agent (open source)

    security.vista-labs.ai

    We've built an open-source tool to stress test AI agents by simulating prompt injection attacks.

    Hacker News8점

  3. Prompt-injection firewall for OpenClaw agents

    github.com

    Anti-Virus for ClawdBot: Prompt Injection Prevention

    Hacker News6점

  4. FireClaw

    github.com

    Open-source proxy defending AI agents from prompt injection

    Hacker News5점

  5. Conduct

    github.com

    open-source guardrails for LLM and MCP tool calls

    Hacker News22점