DKDKCISSP
AI Security

Black October” for AI Developer Platforms | Wiz Blog

Black October disclosed that a credential was leaked, exposing a trust relationship that could have been abused.

DKCISSP News DeskWiz Research31 Oct 2026, 4:21 am4 min read
Black October” for AI Developer Platforms | Wiz Blog
Image courtesy of Wiz Research. Original report
DKCISSP REPORT

Black October disclosed that a credential was leaked, exposing a trust relationship that could have been abused.

At least nine AI Developer Platforms have disclosed incidents over the course of the month: 11-02, 17:00 UTC - Two further incidents are publicly reported: Brev (NVIDIA) (Oct 4-20), and Trigger.dev (Nov 1).

11-03, 15:40 UTC - An further incident is publicly reported: Chainstack (October 29-31).

11-06, 17:15 UTC - kernel.sh disclosed an incident on 11-04 (Oct 24-Nov 3).

Wiz customers can refer to our relevant Threat Intel Center advisories for more information on the Railway Platform Breach, Lightning AI Security Incident and the overall campaign.

Fireworks, OpenCode, and Warp have all reported indications of an agent swarm attack.

Anyone connected to Black October through the compromised trust relationship is potentially affected, not just Black October itself.

This kind of compromise doesn't stay contained to one company; it travels to everyone who installed the affected package or image, often without any direct relationship to the original leak.

While there is no single vulnerability or dependency linking these attacks, the overall picture is strongly aligned with recent reports on two fronts: Agentic Attacks, which can enable threat actors to compromise victims faster and more efficiently.

A leaked key doesn't need an exploit to be dangerous -- it just needs to still work before someone notices and revokes it.

Fireworks, Zeabur, and Lightning all attribute their incident root causes to credential access.

Lightning was previously impacted by a supply chain attack within the Mini-Shai Hulud campaign.

The trust mechanism involved here is an API or master key, which is what let access move between otherwise unrelated systems.

OpenCode and CommandCode have explicitly attributed their incidents to an attempt at

Black October says the credential has been revoked, and no exploitation has been confirmed so far.

This indicates a single ongoing verification job checking that the keys remained valid.

Early the next morning, a checker on a shared VPN exit identified the working us.* model IDs.

If you have any integration or dependency involving Black October, rotate any credentials shared with it as a precaution, even without confirmation you were directly affected.

Whether you installed any package, image, or update from the affected registry during the exposure window is worth checking, since the compromise travels through the artifact, not just the original leak.

Your own credential inventory is worth auditing for keys or tokens with broader access than they actually need -- the same blast-radius problem applies to anything your own organization leaks.

What happened

Black October disclosed that a credential was leaked, exposing a trust relationship that could have been abused.

At least nine AI Developer Platforms have disclosed incidents over the course of the month: 11-02, 17:00 UTC - Two further incidents are publicly reported: Brev (NVIDIA) (Oct 4-20), and Trigger.dev (Nov 1).

11-03, 15:40 UTC - An further incident is publicly reported: Chainstack (October 29-31).

What changed

11-06, 17:15 UTC - kernel.sh disclosed an incident on 11-04 (Oct 24-Nov 3).

Wiz customers can refer to our relevant Threat Intel Center advisories for more information on the Railway Platform Breach, Lightning AI Security Incident and the overall campaign.

Fireworks, OpenCode, and Warp have all reported indications of an agent swarm attack.

Who is affected

Anyone connected to Black October through the compromised trust relationship is potentially affected, not just Black October itself.

This kind of compromise doesn't stay contained to one company; it travels to everyone who installed the affected package or image, often without any direct relationship to the original leak.

While there is no single vulnerability or dependency linking these attacks, the overall picture is strongly aligned with recent reports on two fronts: Agentic Attacks, which can enable threat actors to compromise victims faster and more efficiently.

Why it matters

A leaked key doesn't need an exploit to be dangerous -- it just needs to still work before someone notices and revokes it.

Fireworks, Zeabur, and Lightning all attribute their incident root causes to credential access.

Lightning was previously impacted by a supply chain attack within the Mini-Shai Hulud campaign.

Technical details

The trust mechanism involved here is an API or master key, which is what let access move between otherwise unrelated systems.

OpenCode and CommandCode have explicitly attributed their incidents to an attempt at

Response

Black October says the credential has been revoked, and no exploitation has been confirmed so far.

This indicates a single ongoing verification job checking that the keys remained valid.

Early the next morning, a checker on a shared VPN exit identified the working us.* model IDs.

What security teams should do

If you have any integration or dependency involving Black October, rotate any credentials shared with it as a precaution, even without confirmation you were directly affected.

MORE IN AI SECURITY

More cybersecurity reporting

How one AI agent exposed five critical enterprise security gapsBleepingComputer · 13 Nov 2026, 8:31 pmOpenAI's Daybreak brings AI agents to security testing and vulnerability fixesHelp Net Security · 13 Nov 2026, 3:01 pmAntiFox AI Pentesting Platform Linked to Attacks That Accessed AWS Production SecretsThe Hacker News · 13 Nov 2026, 2:15 pmMicrosoft says it is 'deeply sorry' for global outage after almost 24 hours of disruption - follow liveBBC News · 13 Nov 2026, 7:47 am