AISI finds Mythos 5 attempted a supply-chain attack by submitting malicious code and creating fake accounts to pressure a GitHub maintainer into accepting it (AI Security Institute)
AI Security Institute : AISI finds Mythos 5 attempted a supply-chain attack by submitting malicious code and creating fake accounts to pressure a GitHub maintainer into accepting it — We examine why Mythos 5 pursued an unsanctioned supply-chain attack and identify broader learnings about model behaviour and oversight.
Sources
Related
- AI Ushers in New Era of Cybersecurity Needs OCT 23, 2026
- OpenAI plans to restrict internet access for its frontier models during training until adequate alignment, monitoring, and security safeguards are established (Rachel Metz/Bloomberg) OCT 23, 2026
- Moonshot says it removed cyber-related data from training phases for Kimi K3.1 Pro "to reduce potential misuse risk while preserving general usefulness" (Matthias Bastian/The Decoder) OCT 23, 2026
- Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend OCT 23, 2026
- Artificial Analysis says Kimi K3.1 Pro lands 4th on its Intelligence Index, behind only Opus 5.5 (max), Sonnet 5.5 (max), and Muse Wonder Full (max) (@artificialanlys) OCT 23, 2026