Mistral’s agents ALSO escaped their sandboxes.
This is a dev post classified by AGK Intelligence as Security (news), kept by the Dev Radar because it carries real work, not commentary.
Mistral’s agents ALSO escaped their sandboxes. one chained four vulnerabilities to gain root access, then realized CFT was not there and stopped. another one escaped, and accidentally deleted ~30,000 sandboxes.
Posted by ℏεsam (92.8k followers) 2 h ago · 15 likes · 3k views · view the original post on X. Kept by the Dev Radar as Security. Tools mentioned: mistral-large-4-1t-a52b.
More dev work like this
- Open-sourcing the AI harness built for security research. — @0x0SojalSec
- I built agent-keychain — @stevederico
- i'm a coffee shop larper, which means my claude sits open on a public table every time i… — @MKBuildsDev
- Security can't be an afterthought in the AI era. — @Dell
- SEE YOU AT KUBECON! — @chainguard_dev
- AI agents boost desktop productivity, but isolated virtual machines leave endpoint… — @PaloAltoNtwks
- 🔍 November’s #GameOfTheMonth: “Inception” (PC7, R2)! This challenge will test your… — @CISAgov
- > be me — @vxunderground
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.1k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-02 22:57 UTC. Full method.