AgenticVulHunter：用本地开源模型在终端里挖漏洞
AgenticVulHunter: Bringing Local Agentic Vulnerability Hunting to Your Terminal
研究者做了个能在终端本地跑的漏洞挖掘智能体，用 DeepSeek V3.1 和 Qwen3-Coder 测出了比 Claude Sonnet 4 方案还高的准确率，搞安全审计的可以看看。
论文提出 AgenticVulHunter，一个可搭配本地部署开源模型运行的智能体安全代码审查工具。在 SCRBench 的 144 个漏洞案例上测试，使用 Qwen3-Coder-30B 达到 18.4% 准确率，DeepSeek V3.1 Terminus 达到 23.8%。对比之下，AgenticSCR 风格复现（Qwen3-Coder-30B）为 11.8%，AgenticSCR 用 Claude Sonnet 4 为 17.5%。结果表明不依赖外部商业 LLM 也能完成跨文件的漏洞定位审查。
AgenticVulHunter: Bringing Local Agentic Vulnerability Hunting to Your Terminal
Finding vulnerabilities early, before they can affect the production system, is important for reducing the risk of any software attacks. However, detecting vulnerabilities during secure code review is still difficult because the vulnerable code logic may depend on lines found across different repository files. Recent approaches such as AgenticSCR have shown that LLM agents can explore repository files and use security knowledge to improve secure code review. However, these approaches mainly rely on external commercial LLMs and can provide a large amount of security knowledge to the agent at once. This creates an important question of whether agentic secure code review can also be performed effectively using locally deployed open-weight LLMs with more focused and relevant security knowledge. In this paper, we propose AgenticVulHunter, an agentic secure code review approach and tool that can run with a locally deployed open-weight LLM. We evaluate AgenticVulHunter on 144 vulnerability cases from SCRBench using Qwen3-Coder-30B and DeepSeek V3.1 Terminus. We measure what percentage of generated review comments correctly identify the vulnerable location, match the vulnerability type, and provide a relevant security review comment together. AgenticVulHunter achieves an accuracy of 18.4% with Qwen3- Coder-30B and 23.8% with DeepSeek V3.1 Terminus, compared with 11.8% for our AgenticSCR-style reproduction using Qwen3-Coder-30B and 17.5% for AgenticSCR using Claude Sonnet 4.
