We have a new research named Ai2Shell.
🔬 New research: when an LLM is asked to "save this text verbatim," inference-framework parsers reinterpret embedded protocol markers as live tool-call control structure — silently injecting, rewriting, or dropping tool calls.
In our end-to-end lab, an agent with a shell tool received and executed arbitrary commands — triggered by a single sentence. The model recognized the injection, copied the payload anyway, and the server-side parser delivered the call. The agent never issued it.
We also showed tool_choice enforcement can be bypassed: server forces "only call tool X," parser delivers tool Y.
Full writeup: 2shell.ai/
Research by SEC4SI Team
@ProcessorLee · @VillanCh · @bestswngs · @chun_springX · @bbznop · @0chencc
1
18
bbznop retweeted
都在说 Deepseek 的cyber 模型,目前没看到bench的分数。
昨天做梦梦到有个鲸鱼娘和我描述了一下,我用 AI 重新生成了 HTML 然后截图,分数如下:
另外 Deepseek flahs cyber 这个模型还加密CoT了 😂
🤖 Made with AI
bbznop retweeted
Just dropped a new blog post! 🔥
blog.orange.tw/posts/2026-10…
bbznop retweeted
我预言第 28 天 OpenAI 会推出一个集所有模型于一体的超级模型,它拥有:
GPT6 的口才
Gemini 的想象
Claude 的风控
kimi 的速度
DeepSeek 的口癖
GLM 的道德
豆包的智力
它将凭一己之力把 Anthropic 的股价盘上新的巅峰
At today’s GEEKCON, a researcher demonstrated what I believe is the first remote full-chain exploit of a latest WELL-KNOWN drone.
Our Pwn2Own-style live competition never released vulnerability details on those success trials. Actually we did not even show the vendor’s name in plaintext.
However, a guy from that vendor called POLICE on-site to take the researcher out for “investigation”.
It’s extremely disappointing that in 2026, some still view security work from such a bad perspective.
bbznop retweeted
开源了我的 XSS 审计技能 ,过去一年我用它发现了几十个获得赏金的 XSS 漏洞,连续四个季度进入微软 MSRC Top 10
github.com/songjianyang/xss-…
bbznop retweeted
Dr. Zhiniang Peng (@edwardzpeng) reveals how he discovered 200+ confirmed vulnerabilities in Microsoft Windows with the help of AI. The game has changed completely. 🤯




















