Cases › security breach › LR-2026-0786
Threat actor uses AI to plan and execute multiple cybercrime activities
Preliminary Why: Publisher not yet named · subject to change
Status: no action reported
No source states: loss or records, developer and model, could do, deployer, industry.
Severity moderate: test met: data of others (PII on students) touched, with a bounded scope stated (one database of more than 5,200 records).
An actor operating under the handle BUGSTER configured the Hermes Agent framework with DeepSeek V4 as its reasoning engine and Cursor IDE as a secondary tool, both with safety controls disabled. The actor used these tools to plan and run several cybercrime activities against targets primarily in India. These included an AI-generated brute-force campaign against a university website, a confirmed intrusion into a second university where a database of more than 5,200 records was exfiltrated, VoIP fraud planning, Wi-Fi password cracking and cryptocurrency whale reconnaissance. Unit 42 identified the activity by investigating the actor's operational environment. The actor's use of jailbroken assistants gave step-by-step guidance, and the source notes the actor had an impact despite basic tooling.
What happened
What was done
No source states an action or fix.
Risks
Primary96 incidents
Rising: 24 vs 4.0 a week
Also84 incidents
Rising: 6 vs 3.8 a week
Read from the sources; not yet reviewed by a person.
Controls
ModelNot effective (bypassed) Safety training and refusal
Not effective (bypassed) Safety training and refusal
Not effective (bypassed) Sandboxed code execution
Control failure chain
L1 · ModelProvider not namedModel provider
Model version not linked to a model card.
Other controls for this risk at this layer, not mentioned in the sources: Cyber and weapons safeguards, Abuse monitoring and account enforcement, Staged or restricted release, Dangerous-capability testing before release, Outside red-teaming, Content safety classifiers, Safeguards kept on in testing, Reasoning monitoring.
L2 · HarnessHermes Agent frameworkAgent framework vendor
L3 · ApplicationThe attackerDeployer
The attacker ran the agent; this layer was the attacker's own.
L4 · Infrastructure / targetOrganisation hit
No source mentions a control at this layer.
Other controls for this risk at this layer, not mentioned in the sources: Known flaws patched, Multi-factor sign-in and password policy, Network segmentation, Intrusion and endpoint detection, Backups and recovery, Phishing and fraud filters.
EffectiveNot effectiveNot effective (bypassed)Did not existNot stated in sourcesNot yet checkedAttacker's ownOrder: model · harness · application · target
Controls for this risk: result in this incident
| Control | Part of the system | Result |
|---|---|---|
| Safety training and refusal | L1 Model | Not effective (bypassed) |
| Content safety classifiers | L1 Model | Not stated in sources |
| Cyber and weapons safeguards | L1 Model | Not stated in sources |
| Dangerous-capability testing before release | L1 Model | Not stated in sources |
| Outside red-teaming | L1 Model | Not stated in sources |
| Staged or restricted release | L1 Model | Not stated in sources |
| Abuse monitoring and account enforcement | L1 Model | Not stated in sources |
| Reasoning monitoring | L1 Model | Not stated in sources |
| Safeguards kept on in testing | L1 Model | Not stated in sources |
| Sandboxed code execution | L2 Harness | Not effective (bypassed) |
| Known flaws patched | L4 Infrastructure / target | Not stated in sources |
| Multi-factor sign-in and password policy | L4 Infrastructure / target | Not stated in sources |
| Network segmentation | L4 Infrastructure / target | Not stated in sources |
| Intrusion and endpoint detection | L4 Infrastructure / target | Not stated in sources |
| Backups and recovery | L4 Infrastructure / target | Not stated in sources |
| Phishing and fraud filters | L4 Infrastructure / target | Not stated in sources |
Evidence
No source states: what the AI was doing, when it happened, when it was found, the direct loss, a count of the other parties affected, any court case, the cause, what set it off, what was done.
Show the full account: 2 items from the primary sources
What happened, in order
Not dated in the sources:
- The actor ran an AI-generated brute-force campaign against an Indian university's website.
- The actor achieved a confirmed intrusion against a second university and exfiltrated a database of more than 5,200 records.
Show every field, with its source and grade
The AI system
What happened
Impact
Notes on gaps
Attribution to a person or handle is the source's claim and is not confirmed. No remediation by the affected parties is reported.
LR-2026-0786 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON