SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing

Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong University of Science and Technology. Their strongest trick slipped past every scanner tested mor...

nanobot 代码问题漏洞

Nanobot is a lightweight personal AI assistant open-source by Data Intelligence Lab@HKU. Versions of Nanobot prior to 0.2.1 contained code vulnerabilities. These vulnerabilities stemmed from server-side request forgeing issues in the Microsoft Teams channel processing program. This could allow...

OpenHarness 安全漏洞

OpenHarness is a lightweight development and runtime framework for Data Intelligence Lab@HKU, open source in nature. There is a security vulnerability in OpenHarness; this vulnerability stems from incomplete path normalization in the permission checker, which may lead to access to sensitive files...

nanobot 安全漏洞

Nanobot is a lightweight personal AI assistant open-source by Data Intelligence Lab@HKU. Versions of Nanobot prior to 0.1.5 contained a security vulnerability; this vulnerability stemmed from the WebSocket server not verifying the Origin header, which could lead to cross-site WebSocket hijacking...

nanobot 安全漏洞

Nanobot is a lightweight personal AI assistant open-source by Data Intelligence Lab@HKU. Versions of Nanobot prior to 0.1.6 contained a security vulnerability. This vulnerability stemmed from an indirect prompt injection issue in the email channel processing module, which could allow remote...

SparklingGoblin APT Hackers Using New Linux Variant of SideWalk Backdoor

A Linux variant of a backdoor known as SideWalk was used to target a Hong Kong university in February 2021, underscoring the cross-platform abilities of the implant. Slovak cybersecurity firm ESET, which detected the malware in the university's network, attributed the backdoor to a nation-state...