luckyPipewrench/pipelock
- 类型:github
- 标识:luckyPipewrench/pipelock
- 链接:https://github.com/luckyPipewrench/pipelock
- 主题:agent, risk, llm-infra
- 主分类:agent
- 形态:app
- 分类:skill
- Stars:913
- 周增:+0
- 语言:Go
- 许可:Apache-2.0
- 最近提交:2026-09-30
- 简介:Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
- 上次采集:2026-10-01
- 首次采集:2026-10-01
- 待LLM分类:否
- 成熟度:research
- 简介中文:开源 AI agent 防火墙,用于 MCP 安全与 agent 出站流量防护。扫描经中介的 HTTP、MCP、A2A 与 WebSocket 流量,检测数据外泄、SSRF 与 prompt 注入,并签发由中介签名的操作回执:在 agent 之外生成可验证的审计证据。
- 来源文件:
- [GitHub Search]