Anthropic Claude AI Model Used in GitHub Agentic Workflows Prompt Injection
Anthropic Claude is one of the AI models that can power GitHub Agentic Workflows, which are vulnerable to the GitLost prompt injection…
Tag: AI Security
Webinar: How AI Is Reshaping Supply Chain Security As We Know It
A webinar hosted by OX researchers on July 22, 2026, covering AI integration's impact on attack surface, MCP server findings, and supply…
AI in the Build Pipeline: How Software Supply Chain Security Must Evolve
Software supply chain security was already complex, but the integration of AI into the build pipeline has introduced new risks that traditional…
BeyondTrust Patches Critical Auth Bypass Flaws in Remote Support and PRA
BeyondTrust has released security updates to address multiple critical vulnerabilities in its Remote Support (RS) and Privileged Remote Access (PRA) products. The…
Oasis Security: Cybersecurity Research Firm
Oasis Security is a cybersecurity research firm that disclosed the NemoClaw vulnerability and has previously documented similar techniques against Paperclip and OpenClaw…
SkillCloak: A Technique for Evading Static Scanners in AI Agent Skills
SkillCloak is a technique developed by researchers at the Hong Kong University of Science and Technology that rewrites malicious AI agent skills…
SkillDetonate: A Runtime Checker for Malicious AI Agent Skills
SkillDetonate is a runtime checker developed by the same team behind SkillCloak. It runs skills in a sandbox and monitors OS-level behavior,…
ClawHavoc: A Campaign Distributing Malicious AI Agent Skills
ClawHavoc is a campaign identified by Koi Security that distributed 341 malicious skills on the ClawHub marketplace, later growing to 824. These…
Hong Kong University of Science and Technology: Research on AI Agent Security
Researchers at the Hong Kong University of Science and Technology developed SkillCloak and SkillDetonate, tools that demonstrate vulnerabilities in static scanning of…
SkillCloak Technique Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing
Researchers at the Hong Kong University of Science and Technology have developed a technique called SkillCloak that allows malicious AI agent skills…