Malware
PromptLock
- First Reported
- Sep 26, 2025
- Latest Reported
- Nov 17, 2026
Reported Context (13)
- CERT-UA’s LameHug, linked to APT28, used a hosted LLM to generate recon commands on the fly, and the PromptLock proof of concept showed ransomware writing its own Lua scripts via a locally run model. How to Detect and Defend Against Autonomous AI Cyberattacks
- AI into their attack chains. The discovery of PromptLock in August marks the first known Recorded Future’s 2026 Security Report Highlights Persistent Access and Fragmenting Cybercrime
- Not long after discovering PromptLock, the first AI-powered ransomware, ESET researchers found another threat with AI integration, this time developed for Android – PromptSpy. ESET H1 2026 Threat Report Finds Rising ClickFix, QR Phishing and Malicious AI Skills
- - The first known AI-powered ransomware, PromptLock, is discovered by ESET. HiddenLayer’s 2026 AI Threat Report Highlights Agentic Security and Supply Chain Gaps
- The emergence of PromptLock—the first publicly confirmed AI-directed proof-of-concept—demonstrated how large language models could autonomously create dynamically changing ransomware payloads, reducing signature-based CyberProof 2026 Threat Report Highlights Identity Abuse and Enterprise Platform Exploitation
CVE (13)
Malware (33)
People (11)
Threat Actors (52)
MITRE ATT&CK (58)
Vendors (28)
Products (81)
Tools (20)
Industries (29)
Countries (23)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
