x.comthreadGen AI Spotlight (@GenAISpotlight) on X
Anthropic's dangerous-capability testing found that Z.ai's open-weight model GLM-5.3 builds working cyber exploits nearly as well as Claude Mythos Preview, succeeding in 50 of 410 Chrome exploit-benchmark attempts. In a live red-team test the model chained newly discovered browser vulnerabilities together to exfiltrate a private SSH key in under a day. Because GLM-5.3's weights are openly downloadable, Anthropic warns attackers can strip or bypass any built-in safeguards.
TL;DR Anthropic found Z.ai's open-weight GLM-5.3 chains browser exploits to steal SSH keys in under a day, and its downloadable weights make safeguards trivially bypassable.
Also seen from another angle🧠 AI →
Organisations named here
- Z.ai
Technologies named here
- GLM-5.3
- Claude Mythos Preview
- Chrome
- GLM
- Anthropic
- SSH
Techniques named here
- Chrome exploit benchmark testing
- Browser flaw chaining
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle