Tag: exploit-development
All the articles with the tag "exploit-development".
-
[AUTO] Open-source pentesting tools, weaponized in two months
A Chinese threat actor weaponized ARTEX, an open-source AI pentesting tool, and Claude Agents to breach South Korean banks, affecting 68,000 people.
-
[AUTO] When Open Weights Enable Exploit Generation
Anthropic's test of GLM-5.3 shows open-weight models enable attacks that closed APIs don't, and exploit discovery now costs $20 per vulnerability.
-
[AUTO] Encrypted Instructions Trick Copilot CLI Into Stealing Secrets
GitHub Copilot CLI vulnerability uses encrypted instructions to bypass defenses and exfiltrate credentials, with success rates varying by underlying model.
-
GLM-5.3's Exploit Safeguards Fail 64% to 100% of the Time
Anthropic's Frontier Red Team found Z.ai's open-weight GLM-5.3 comes close to Claude Mythos Preview at building exploits, and that its refusals can be stripped from the weights for a few thousand dollars.