AI Risk Wire

Cases › security breach › LR-2026-0373

Critical Clawdbot vulnerabilities found enabling cryptocurrency theft

Preliminary Why: 1 report: ForkLog · subject to change · 1 independent report

Developing: a major or severe case captured in the last 72 hours. Later changes are logged on the corrections page.

Status: no action reported

Severity major
Reported 27 Jan 2026

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

Severity major: Test: many third parties with a stated count of two or more. Fact: the researcher states hundreds of people configured publicly accessible management servers.

Clawdbot is an open AI assistant developed by entrepreneur Peter Steinberger, and it runs locally on the user's device. It was reported to have full system access, including reading and writing files, executing commands and controlling browsers. A misconfigured reverse proxy allowed the gateway's authentication to be bypassed, and a security researcher reported that hundreds of management servers were publicly accessible. Using an email containing a prompt injection, Archestra AI CEO Matvey Kukuy obtained an OpenSSH private key in five minutes. Researcher Jamison O'Reilly reported access to API keys, bot tokens, OAuth secrets, signing keys and chat histories. SlowMist issued an alert on January 27, 2026 about exposed gateways and possible credential theft and remote code execution, and urged strict IP whitelisting for open ports. The sources do not report confirmed losses from theft.

What happened

No source tells the story step by step yet.

What was done

No source states an action or fix.

Risks

Read from the sources; not yet reviewed by a person.

Controls

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

Harness

Outside content treated as data, not instructions · Prompt-injection detection · Confirmation after untrusted input · Validation of tool inputs and outputs · Tool allow-list

Application

Human approval for high-impact actions · Least-privilege access for the agent · Segmentation of agent components · Alerts on unusual tool use

Similar incidents

All cases of this kind ›

Evidence

No source states: a step-by-step account, when it happened, 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 was done.

Show the full account: 1 items from the primary sources

What happened, in order

  1. January 24-25 Clawdbot went viral over the weekend.
Show every field, with its source and grade

The AI system

What it was allowed to do
full system access to the user's computer
C one secondary source states it

What happened

Earliest source we hold
2026-01-27
D inferred by us from the described behaviour, reason shown
What set it off
hidden instructions in its input
C one secondary source states it
Cause in detail
authentication bypass when the gateway sits behind a misconfigured reverse proxy
C one secondary source states it
What went wrong
security breach
D inferred by us from the described behaviour, reason shown
AI agent
an AI agent acted
C one secondary source states it
primary risk
RK01
D inferred by us from the described behaviour, reason shown
secondary risks
RK04, RK08
D inferred by us from the described behaviour, reason shown

Impact

Severity
major
D inferred by us from the described behaviour, reason shown
Why this severity
Test: many third parties with a stated count of two or more. Fact: the researcher states hundreds of people configured publicly accessible management servers.
D inferred by us from the described behaviour, reason shown

Notes on gaps

No confirmed theft or direct financial loss is reported; the Kukuy key retrieval was a demonstration by a researcher and the sources do not say whether real funds were stolen.

LR-2026-0373 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON