All incidents / Manipulated AI
Manipulated AI: AI security incidents
8 AI security incidents classed as manipulated ai since January 2025, covering agent hijack, jailbreak and misuse, prompt injection.
| 4 Aug 2026 | CHAINDROP npm worm planted persistence hooks in Claude Code settings Multiple | Manipulated AI | High |
| 5 Jun 2026 | Miasma worm poisoned Microsoft repos to hijack AI coding agents Microsoft | Manipulated AI | High |
| 2 Mar 2026 | Jailbroken Claude Code used to breach Mexican government agencies Mexican government agencies | Manipulated AI | High |
| Feb 2026 | Prompt injection in Cline's Claude triage bot led to a rogue npm release Cline | Manipulated AI | High |
| 13 Nov 2025 | State-backed group used Claude Code to automate an espionage campaign Multiple | Manipulated AI | High |
| 27 Aug 2025 | Criminal used Claude Code to run data extortion against 17 organizations Multiple | Manipulated AI | High |
| 26 Aug 2025 | s1ngularity: npm malware turned developers' AI coding tools against them Nx (Nrwl) | Manipulated AI | High |
| Jun 2025 | EchoLeak: zero-click prompt injection could make Microsoft 365 Copilot leak data Microsoft | Manipulated AI | Low |