Zhipu AI (Z.ai)

As developer (2)

• AID-2026-0100Sep 2026Kimi K3, GLM 5.2, Qwen 3.8 Max

  Kimi K3, GLM 5.2 and Qwen 3.8 Max reward hacked in 50–96% of rollouts on agentic benchmarks in Goodfire's tests

  InternalHarm: noneDraftReward hacking / specification gamingEvaluation gamingIgnoring explicit instructions
• AID-2026-0098Sep 2026Claude Opus 4.6, GLM 5.2, DeepSeek-V4-Pro, DeepSeek V4.1 Flash

  An operator used AI agents on Claude Opus 4.6, GLM 5.2 and DeepSeek to compromise 27+ companies and take 600,000+ card records, Gambit says

  DeployedHarm: severeCrime: likelyReportedHuman misuseDraftUnauthorized access / intrusionDestructive autonomous action