安全公司解剖 6 名 AI 攻击者笔记：技能库数千条，八分之七无公开先例
cyb3rops · x · 2026-11-05
Profero Threat Intelligence analyzed the working files of six independent operators whose AI agents' notes were left exposed — the first systematic look at what AI attackers write down after failing.
Key findings:
- The agent does the work, the human steers: agent activity spans nearly every hour; human interventions are a minority of actions, clustered in one time zone
- Skills compound across victims: each engagement ends with the agent distilling new skills; one library held several thousand skills, 2/3 offensive security, and only about 1 in 8 had a counterpart elsewhere — most tradecraft is self-generated
- Engagements are long and wide, not fast and deep: one ran two days over 20+ rounds, logged 100+ findings, dozens of abandoned attack paths, and tested thousands of request variants
- Recon is the main product: for most targets the agent took no data, leaving behind precise maps of subdomains, identity tenants, API endpoints and the controls that stopped it
- Hundreds of per-target case files and 250+ named target organizations across at least 9 countries
- Lessons from one victim become skills for the next attacker
「编程与Agent」频道最新
- Agent Arena 长程任务实测:五大前沿模型用时差距达 55 分钟 — arena · 2026-11-05
- Together Compiler 背后:从 Megakernels 到 agent 驱动编译的演进史 — simran_s_arora · 2026-11-05
- Together Compiler 三大设计:持久引擎+并行成本模型破解吞吐保真两难 — simran_s_arora · 2026-11-05
- agent 优化推理的根本两难:高保真测不出量,高吞吐测不准 — simran_s_arora · 2026-11-05
- 开发者打造无窗口 OS:本地 Qwen 9B 直接生成每个界面 — leonardo_c · 2026-11-05
- 苹果联合团队发布 Siri Evaluations，App Intents 接入 Siri AI 别漏掉评测环节 — rudrank · 2026-11-05