AI News AI资讯 22h ago Updated 1h ago 更新于 1小时前 48

Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities 谷歌开源Mantis:让编程智能体发现、复现和修复漏洞的模块化技能工具包

Google open-sourced Mantis, a modular, stack-agnostic security review toolkit that enables AI coding agents to execute the full vulnerability lifecycle from detection to patch verification Mantis operates as a chain of slash-command skills rather than a standalone scanner, integrating with frameworks like Gemini CLI, Antigravity CLI, and Google ADK Its key differentiator is sandboxed reproduction and patch re-attack as the trust boundary, addressing the sub-7% true-positive rate of naive AI code Google开源Mantis,一个模块化安全审查技能工具包,使AI编码代理能运行完整的漏洞生命周期(发现→复现→修复→风险评估) 采用斜杠命令架构集成到现有编码代理,而非独立扫描器,通过沙箱执行和补丁重攻击验证降低误报率 当前支持本地/内部评估(兼容Gemini CLI、Antigravity CLI等),尚未推荐生产部署 分层摘要树技术可减少85%以上的token开销,针对传统AI代码扫描<7%真实阳性率问题设计

72
Hot 热度
65
Quality 质量
68
Impact 影响力

Analysis 深度分析

TL;DR

  • Google open-sourced Mantis, a modular, stack-agnostic security review toolkit that enables AI coding agents to execute the full vulnerability lifecycle from detection to patch verification
  • Mantis operates as a chain of slash-command skills rather than a standalone scanner, integrating with frameworks like Gemini CLI, Antigravity CLI, and Google ADK
  • Its key differentiator is sandboxed reproduction and patch re-attack as the trust boundary, addressing the sub-7% true-positive rate of naive AI code scanning
  • A hierarchical summary tree reduces token overhead by over 85%, and a newer /mantis-advise skill enables proactive prevention by querying threat models before code is written
  • Currently deployable for local and internal evaluation under Apache 2.0, but not yet recommended for production use

Why It Matters

Mantis represents a significant shift in agentic security tooling by moving beyond passive vulnerability scanning to active, sandboxed proof-and-fix workflows that dramatically improve signal quality. For AI practitioners building coding agents, it provides a modular, interoperable framework that can be integrated into existing development pipelines without requiring a proprietary scanner. The emphasis on deterministic inter-stage contracts over LLM-driven orchestration offers a pragmatic path toward trustworthy automated security review.

Technical Details

  • Mantis is structured as a sequence of modular skill directories invoked as slash commands, orchestrated either sequentially or by a supervisor skill (/mantis-meta-agent) in long-lived sessions
  • The pipeline is divided into three phases: early stages (/mantis-history, /mantis-summarize, /mantis-architecture, /mantis-threat-model, /mantis-plan) learn the codebase and produce a targeted roadmap; middle stages (/mantis-researcher, /mantis-dedupe, /mantis-review, /mantis-critic) sweep files, collapse duplicates, and filter false positives; late stages (/mantis-reproduce, /mantis-chain, /mantis-patch, /mantis-calibrate, /mantis-reflect, /mantis-report) execute payloads in gVisor or VMs with disabled networking, assemble exploit chains, verify patches, and score residual risk from 1 to 10
  • /mantis-advise inverts the traditional flow by querying accumulated threat models, past bug lineages, and verified patch patterns proactively before code is written, preventing recurrence of known vulnerability classes
  • The toolkit enforces strict execution rules about where the coding agent is allowed to run code, and publishes inter-stage contracts to enable deterministic harness wrapping instead of relying on LLMs to orchestrate shell commands
  • Compatible with Gemini CLI, Antigravity CLI, Google ADK, and comparable agent frameworks; released under Apache 2.0

Industry Insight

  • The sub-7% true-positive rate cited for naive AI code scanning highlights a critical industry pain point; Mantis's sandboxed reproduction and re-attack methodology offers a blueprint for turning noisy AI-generated findings into actionable, verified security intelligence
  • The modular slash-command architecture and published inter-stage contracts enable organizations to adopt incremental security automation without vendor lock-in, making it easier to integrate agentic security workflows into existing CI/CD pipelines
  • The proactive /mantis-advise skill signals a broader industry shift from reactive vulnerability scanning to preventive security guidance embedded directly in the coding agent workflow, which could become a standard expectation for AI-assisted development tools

TL;DR

  • Google开源Mantis,一个模块化安全审查技能工具包,使AI编码代理能运行完整的漏洞生命周期(发现→复现→修复→风险评估)
  • 采用斜杠命令架构集成到现有编码代理,而非独立扫描器,通过沙箱执行和补丁重攻击验证降低误报率
  • 当前支持本地/内部评估(兼容Gemini CLI、Antigravity CLI等),尚未推荐生产部署
  • 分层摘要树技术可减少85%以上的token开销,针对传统AI代码扫描<7%真实阳性率问题设计

为什么值得看

Mantis为AI安全工具链提供了可验证的漏洞管理范式,其沙箱复现与补丁重攻击机制直接解决行业长期存在的误报率痛点。模块化设计允许团队将安全审查无缝嵌入现有AI代理工作流,对构建可信自动化开发流程具有示范价值。

技术解析

  • 架构设计:以独立技能目录形式发布,通过/mantis-meta-agent等斜杠命令串联工作流,支持确定性编排而非依赖LLM直接控制shell命令
  • 三阶段流水线:早期阶段(/mantis-history等)构建威胁模型与代码知识图谱;中期阶段(/mantis-researcher等)执行定向扫描与误报过滤;后期阶段(/mantis-reproduce等)在gVisor/VM沙箱中验证漏洞并生成修复补丁
  • 性能优化:采用分层摘要树结构,据Google数据可减少85%以上token消耗,提升大规模代码库处理效率
  • 部署兼容性:开源协议为Apache 2.0,可集成至Gemini CLI、Google ADK等主流代理框架,但官方明确标注仅适用于本地测试环境

行业启示

  • AI安全工具正从"发现型"向"验证型"演进,沙箱化漏洞复现将成为可信自动化开发的标准配置
  • 模块化技能设计模式为安全工具集成提供新路径,团队可基于开放接口构建定制化审查流水线
  • 当前工具成熟度仍处早期阶段,建议企业优先在内部测试环境验证,关注后续生产级适配进展

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Open Source 开源 Security 安全 Agent Agent Code Generation 代码生成 Programming 编程