ai-exploitation

新披露的 PHP2Shell 漏洞在公开数小时内引发数百万次利用尝试，而 AI 工具既帮助研究人员发现并利用了这些长期存在的漏洞，也使攻击者能更快地 weaponize 安全缺陷。

Wiz disclosed PHP2Shell, two critical decade-old PHP vulnerabilities that researchers turned into working exploits in about a week with help from Gemini and GPT models, prompting emergency patching and raising questions about AI-driven exploitation of legacy code.

This article discusses how rumors of security bugs in open-source software are being rapidly exploited by AI agents, necessitating changes in security response protocols and highlighting the ineffectiveness of traditional embargoes.

Malware developers are embedding references to nuclear and biological weapons in spyware to trigger LLM safety refusals, evading AI-powered security scanners. This highlights a second-order blindspot in AI safety alignment that attackers are starting to exploit.

Google reports that criminal hackers utilized artificial intelligence to discover a critical software vulnerability, prompting the tech giant to intervene and mitigate the threat before mass exploitation could occur.