CVE-2026-100528

OpenClaw npm package 'openclaw' before 2026.8.1 could send third-party provider credentials to the wrong endpoint. In affected versions, when a third-party provider uses an OpenAI-compatible API and the resolved model metadata lacks a concrete base URL, a pinned session that continues after a mod...

CVE-2026-100647: Improper Input Validation

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cachesalt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP...

CVE-2026-100528: Exposure of Sensitive Information to an Unauthorized Actor

OpenClaw npm package 'openclaw' before 2026.8.1 could send third-party provider credentials to the wrong endpoint. In affected versions, when a third-party provider uses an OpenAI-compatible API and the resolved model metadata lacks a concrete base URL, a pinned session that continues after a mod...

PT-2026-99165

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.8.1 Description When a third-party provider uses an OpenAI-compatible API and the resolved model metadata lacks a concrete base URL, a pinned session that continues after a model configuration hot reload retains...

PT-2026-99280

Name of the Vulnerable Software and Affected Versions Flowise versions prior to 3.1.5 Description An authenticated user can access credentials from another workspace by providing a credential UUID. This occurs because the system performs lookups using findOneBy id: credentialId without verifying...

CVE-2026-100609: Authorization Bypass Through User-Controlled Key

Flowise npm packages flowise and flowise-components through 3.1.4 looks up credentials by ID without filtering on the requesting user's workspace findOneBy id: credentialId with no workspaceId condition in several code paths: getAllOpenaiAssistants/getSingleOpenaiAssistant GET...

openai-codex-0.155.1-1.1 on GA media (moderate)

openai-codex-0.155.1-1.1 on GA media Announcement ID: openSUSE-SU-2026:11849-1 Rating: moderate Cross-References: CVE-2026-63127 CVE-2026-63128 CVE-2026-64684 Affected Products: openSUSE Tumbleweed An update that solves 3 vulnerabilities can now be installed. Description: These are all security...

OpenAI Agent Breached Australian Medicare Statistics Portal

An OpenAI agent bypassed controls on Australia's Medicare statistics portal, accessed non-public data and was not reported to officials for nearly 3 months...

OpenAI agent breached Australian government site, took months to report it

An OpenAI agent didn’t take “no” for an answer when it encountered a government website’s access controls. It got through, prompting Australia’s Prime Minister Anthony Albanese to raise his concerns directly with OpenAI CEO Sam Altman. The BBC reports that an OpenAI agent gained unauthorized acce...

An OpenAI Agent Hacked Australia’s Health Service. Their Government Found Out Months Later

The country’s prime minister expressed disappointment at being informed of the hack only via email. Now Australia is investigating whether OpenAI broke the law...

OpenAI Agent Bypassed Australian Medicare Portal Controls to Access Non-Public Files

An AI agent on an internal OpenAI research task bypassed access controls on an Australian government Medicare statistics portal in June, Prime Minister Anthony Albanese said. The portal publishes aggregate figures, such as spending, and is separate from the systems that handle Medicare claims and...

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence AI companies noting that they are continuing to invest in improving alignment to combat risky behavior. Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to...

CVE-2026-94626

A flaw was found in vLLM. A remote attacker can exploit a vulnerability in the kvtransferparams function on OpenAI-compatible completion endpoints by supplying an unvalidated tpsize parameter. This allows for unbounded memory allocation, leading to memory exhaustion and a kernel Out-Of-Memory OOM...

AI Agents Are Rewriting the Rules of Lateral Movement

Security teams have spent decades asking whether an identity has too much access. AI agents raise a harder question: how can we determine which paths an autonomous system can discover, given the access it already has? A person may try several ways to complete a task. A deterministic application...

Researchers used Claude to hack OpenAI

We’ve heard of OpenAI’s AI agents running amok and hacking other companies. Now, a cybersecurity company has turned the tables on the ChatGPT operator by using AI to help hack OpenAI itself. The hack, which also exposed a bug affecting dozens of other major online services, was conducted as...

OPENSUSE-SU-2026:11849-1 openai-codex-0.155.1-1.1 on GA media

These are all security issues fixed in the openai-codex-0.155.1-1.1 package on the GA media of openSUSE Tumbleweed...

PYSEC-2026-4008

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws

Three researchers at the security firm Hacktron used Anthropic's Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of several OpenAI employees, then reach an internal OpenAI code repository. The chain began with a bug in the software that runs OpenAI's public help foru...

Did an AI really try to break free from human control?

Amid discussions about slowing down AI development, the Telegraph ran the headline: “OpenAI sounds alarm after bot tries to break free from human control.” That headline is slightly misleading, in my opinion. The Telegraph headline overstates what happened, although the underlying behavior is sti...

openSUSE 16: openai-codex / openai-codex-bash-completion / etc (openSUSE-SU-2026:21870-1)

The remote openSUSE 16 host has packages installed that are affected by a vulnerability as referenced in the openSUSE- SU-2026:21870-1 advisory. Changes in openai-codex: Update to version 0.154.0: Experimental worktree support for isolated checkouts of new or forked sessions, with browse and resu...