promptlock
E-mail alert on newly attributed CVEs, new victims in Brazil and verified incidents.
About the group
First known AI-powered ransomware. The PromptLock malware uses the gpt-oss:20b model from OpenAI locally via the Ollama API to generate malicious Lua scripts on the fly
Exploited vulnerabilities
No CVEs attributed to this group in public sources (MITRE ATT&CK). Absence of attribution does not mean absence of activity.
Detection 7
The package a security team uses to hunt for the group in its own environment: the indicators (IOCs) and the YARA rules, from open intelligence on the group.
SHA-1 6
- 161cdcdb46fb8a348aec609a86ff5823752065d2
- 24bf7b72f54aa5b93c6681b4f69e579a47d7c102
- 639dbc9b365096d6347142fcae64725bd9f73270
- ad223fe2bb4563446aee5227357bbfdc8ada3797
- bb8fb75285bcd151132a3287f2786d4d91da58b8
- f3f4c40c344695388e10cbf29ddb18ef3b61f7ef
promptlock.yar
With the plan, you download the YARA rules and the full package, with every indicator.
These plans deliver the raw intelligence:
- the addresses of the groups' leak and negotiation sites;
- the victims' names;
- the full negotiation chat;
- each group's YARA rules and full detection package;
- the criminals' contacts (email, .onion, Tox) unmasked.
They also include webhook, Slack and Discord alerts, the MCP for AI assistants and more API volume. Enterprise is by request.
See the plansDefensive content: use it only in environments you are authorized to analyze. Source: open intelligence on the group · updated on 16 Nov 2026
promptlock uses real techniques and exploits real flaws. TrueHacking's AI Autonomous Pentest simulates these attacks against your infrastructure and brings more security to your application.
Explore the AI Autonomous Pentest →