When AI Coding Agents Pull the Wrong Dependency: How a Trojaned PyPI Release Against LiteLLM Triggered Autonomous EDR and Stopped a Chain Reaction

Related Vulnerabilities

• CVE-2026-35670: OpenClaw before 2026.3.22 contains a webhook reply delivery vulnerability that allows attackers to r MEDIUM
• CVE-2026-40150: PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the web_crawl() function in praison HIGH
• CVE-2026-6011: A weakness has been identified in OpenClaw up to 2026.1.26. Affected by this issue is some unknown f MEDIUM
• CVE-2026-40217: LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting HIGH
• CVE-2026-5999: A vulnerability has been found in JeecgBoot up to 3.9.1. This impacts an unknown function of the com MEDIUM

Related Coverage

• APT37利用朝鲜政治话题针对韩国的攻击活动分析 — DBAPPSecurity · Recent
• 2023年全球勒索软件态势研究报告 — DBAPPSecurity · Recent
• FaCai团伙利用APT技术针对国内的攻击活动分析 — DBAPPSecurity · Recent
• 韩国“伪猎者”APT组织利用多款国产化软件漏洞对中国的攻击活动 — DBAPPSecurity · Recent
• Patchwork APT以中国高校信息办通知为诱饵的攻击事件分析 — DBAPPSecurity · Recent
• 全球最为猖獗的勒索组织LockBit遭到执法部门打击,或将取缔 — DBAPPSecurity · Recent
• 2023全球高级威胁态势研究报告 — DBAPPSecurity · Recent
• 防勒索不能只靠事后救援 — DBAPPSecurity · Recent

Threat Actors

• MuddyWater (Iran)
• Slingshot (US/UK)
• Energetic Bear (Russia)
• APT-Q-92 (US/UK)