From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

  • 类型:arxiv
  • 标识:2605.10834
  • 链接:https://arxiv.org/abs/2605.10834
  • 主分类:evaluation
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This paper presents a practical evaluation protocol that shifts assessment from task completion to validated vulnerability discovery, allowing evaluation in sufficiently complex targets spanning multiple attack surfaces and vulnerability classes, and combines structured ground-truth with LLM-based semantic matching to identify vulnerabilities.
  • OpenAlex ID:W7160950424
  • OpenAlex DOI:10.48550/arxiv.2605.10834
  • DOI:10.48550/arxiv.2605.10834
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2605.10834
  • OpenAlex更新:2026-07-19
  • 副分类:agent
  • 待LLM分类:否
  • 标题中文:从受控环境到真实世界:面向实际场景的渗透测试 Agent 评估
  • TLDR中文:本文提出一种实用评估协议,将评估重点从任务完成转向经过验证的漏洞发现,可在涵盖多种攻击面与漏洞类型的足够复杂目标上开展评估,并结合结构化真值标注与基于 LLM 的语义匹配来识别漏洞。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-16-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • /inbox/tom/_candidates/2026-07-17-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]