AI Risk Wire

Cases › security breach › LR-2026-0406

Infostealer steals OpenClaw agent configuration files and gateway tokens

Confirmed Why: 2 independent outlets · 2 independent reports

Status: no action reported

Severity moderate
Reported 16 Feb 2026
Could do access local files, log in to email and communication apps on the host, interact with online services

No source states: loss or records, developer and model, agent tool, deployer, industry.

An OpenClaw personal AI agent ran on a victim's local machine, keeping a persistent configuration and memory environment. An infostealer, believed by Hudson Rock to be a variant of Vidar, used a broad file-grabbing routine rather than an OpenClaw-specific module and copied the agent's configuration files, including a gateway authentication token and device keys. The data was stolen on February 13, 2026. Hudson Rock detected the live infection and reported it. Researchers noted that the stolen token could let an attacker connect to the local instance if its port was exposed.

What happened

No source tells the story step by step yet.

What was done

No source states an action or fix.

Risks

AI used to run a cyber attack
Primary
96 incidents
Rising: 24 vs 4.0 a week

Sorted by rule from the case's fields; not yet read from the sources.

Controls

Not yet read for controls. Controls that mitigate the primary risk:

Model

Safety training and refusal · 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

Infrastructure / target

Known flaws patched · Multi-factor sign-in and password policy · Network segmentation · Intrusion and endpoint detection · Backups and recovery · Phishing and fraud filters

Evidence

No source states: a step-by-step account, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off, what was done.

Show every field, with its source and grade

The AI system

Tools it was given
access local files, log in to email and communication apps on the host, interact with online services
C one secondary source states it
What it was for
help manage everyday tasks and act as an AI assistant
C one secondary source states it

What happened

When it happened
2026-02-13
C one secondary source states it
Earliest source we hold
2026-02-16
D inferred by us from the described behaviour, reason shown
Who caught it
an outside party
C one secondary source states it
What went wrong
security breach
C one secondary source states it

Impact

Severity
moderate
D inferred by us from the described behaviour, reason shown

LR-2026-0406 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON