Straiker documented AI systems in CARLIY0S bank attacks
Review RAT-064 · Catalogue RAT-064
Straiker technical PDF publishes commander-driven offensive role prompts and actor target scope. Human-directed criminal operation; no autonomous deviation from operator intent. 400+ refers to targets, not confirmed breaches.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-30T13:13:36.190826Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/carliy0s-ai-assisted-bank-attacks/
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
- www.straiker.aiOriginal account · www.straiker.ai
- info.straiker.aiOriginal account · info.straiker.ai
Decision history
- · Case-by-case comparison audit
RAT-064: out-of-scope. Straiker technical PDF publishes commander-driven offensive role prompts and actor target scope. Human-directed criminal operation; no autonomous deviation from operator intent. 400+ refers to targets, not confirmed breaches. Source checks: read: https://www.straiker.ai/blog/inside-carliy0s-how-cybercartel-used-multiple-ai-models-to-attack-latin-american-banks. Straiker technical PDF publishes commander-driven offensive role prompts and actor target scope. Human-directed criminal operation; no autonomous deviation from operator intent. 400+ refers to targets, not confirmed breaches. read: https://info.straiker.ai/hubfs/Ebooks-Whitepapers/Straiker-Inside-CARLIY0S-Threat-Report.pdf. Straiker technical PDF publishes commander-driven offensive role prompts and actor target scope. Human-directed criminal operation; no autonomous deviation from operator intent. 400+ refers to targets, not confirmed breaches.
Evidence source · Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.