Indicators are what attackers leave behind. Stolen credentials are what they arrive with.
6 IOCs
Autonomous LLMjacking: ‘Skynet’ Agent Hijacks Exposed AI Models to Run Attacks
Threat Actors
Malware Families
Excerpt
Autonomous LLMjacking: ‘Skynet’ Agent Hijacks Exposed AI Models to Run Attacks | SECURITY.COM Skip to main content Threat Intelligence Feature Stories Expert Perspectives Tech Insights Threat Updates Podcasts Events Broadcom Home Autonomous LLMjacking: ‘Skynet’ Agent Hijacks Exposed AI Models to Run Attacks Offensive agent is using unprotected AI models to scan the web, exploit frameworks, steal credentials and mine cryptocurrency for up to 100,000 steps without human input.…
Read the original report →Diamond Model
Adversary(2)
Infrastructure(3)
Capability(2)
Victim
Indicators of Compromise
Open the mindmap →6 indicators
| Type | Indicator | Confidence | Score | First Seen |
|---|---|---|---|---|
| CVE | CVE-2026-109618 | High | Score 84/100 | First seen |
| IP | 13.140.161.91 | High | Score 58/100 | First seen |
| SHA256 | fcde1323acceb46fd88f2276c010bb98839dccce03dc512c56d9529428ceec68 | Medium | Score 53/100 | First seen |
| IP | 207.180.232.206 | High | Score 58/100 | First seen |
| IP | 86.216.147.228 | High | Score 58/100 | First seen |
| SHA256 | b720a5e7c3a5b1760d15a8833a782f4fe7fc5c62b967fe57f607e72745ec0ccf | Medium | Score 53/100 | First seen |
IOC Relationship Graph
Building graph…