CVE-2026-4399

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

CVE-2026-4399 Multiple vulnerabilities in 1millionbot Millie chatbot

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

PT-2026-29219

Name of the Vulnerable Software and Affected Versions 1millionbot Millie chatbot affected versions not specified Description A prompt injection issue exists in the 1millionbot Millie chatbot. This occurs when a user bypasses chat restrictions using Boolean prompt injection techniques, constructin...

PT-2026-29445

@jxnlco @emilyzsh I think he is referring to that recent CVE-2026-4417 — OpenAI Codex vulnerability where excessive usefulness leads to immediate $200/month spend escalation. No patch available; users report “this is actually worth it” before wallet compromise...

OpenAI Codex Vulnerability Allowed Attackers to Steal GitHub Tokens

OpenAI Codex vulnerability allowed attackers to steal GitHub tokens via malicious branch names using hidden Unicode command injection flaw...

CVE-2026-26209 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-12.9, vllm-openai-cuda-12.9, py3-cbor2, tritonserver-backend-vllm-cuda-13.0, py3-vllm-cuda-12.4, localstack...

GHSA-3C37-WWVX-H642 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-12.9, vllm-openai-cuda-12.9, py3-cbor2, tritonserver-backend-vllm-cuda-13.0, py3-vllm-cuda-12.4, localstack...

CVE-2026-25083

GROWI OpenAI thread/message API endpoints do not perform authorization. Affected are v7.4.5 and earlier versions. A logged-in user who knows a shared AI assistant's identifier may view and/or tamper the other user's threads/messages...

EUVD-2026-14518

New API: IDOR in VideoProxy allows cross-user video content access via missing ownership check...

CVE-2026-30886

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to version 0.11.4-alpha.2, an Insecure Direct Object Reference IDOR vulnerability in the video proxy endpoint GET /v1/videos/:taskid/content allows any authenticated user to access video...

CVE-2026-30886 New API: IDOR in VideoProxy allows cross-user video content access via missing ownership check

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to version 0.11.4-alpha.2, an Insecure Direct Object Reference IDOR vulnerability in the video proxy endpoint GET /v1/videos/:taskid/content allows any authenticated user to access video...

agent-skill-poc

Agent Skill POC - LLM-driven Interactive CLI Agent An LLM-dri...

Investing in the people shaping open source and securing the future together

Open source has always been about community. It's about maintainers who review pull requests late at night. Volunteers who respond to security reports from strangers. And communities that quietly power the world's software. The reality behind the commits is that maintainers get stretched thin. Th...

EUVD-2026-12343

GROWI OpenAI thread/message API endpoints do not perform authorization. Affected are v7.4.5 and earlier versions. A logged-in user who knows a shared AI assistant's identifier may view and/or tamper the other user's threads/messages...

CVE-2026-25083

GROWI OpenAI thread/message API endpoints do not perform authorization. Affected are v7.4.5 and earlier versions. A logged-in user who knows a shared AI assistant's identifier may view and/or tamper the other user's threads/messages...

ClickFix Campaigns Spread MacSync macOS Infostealer via Fake AI Tool Installers

Three different ClickFix campaigns have been found to act as a delivery vector for the deployment of a macOS information stealer called MacSync. "Unlike traditional exploit-based attacks, this method relies entirely on user interaction – usually in the form of copying and executing commands –...

Missing authorization in the OpenAI thread/message API endpoints of GROWI

Overview GROWI provided by GROWI, Inc. contains the following vulnerability. Missing authorization in the OpenAI thread/message API endpoints CWE-862 - CVE-2026-25083 This can be exploited only when an attacker knows a shared AI assistant's identifier Sho Odagiri of GMO Cybersecurity by Ierae, In...

CVE-2026-25083

GROWI OpenAI thread/message API endpoints do not perform authorization. Affected are v7.4.5 and earlier versions. A logged-in user who knows a shared AI assistant's identifier may view and/or tamper the other user's threads/messages...

CVE-2026-25083

GROWI OpenAI thread/message API endpoints do not perform authorization. Affected are v7.4.5 and earlier versions. A logged-in user who knows a shared AI assistant's identifier may view and/or tamper the other user's threads/messages...

CVE-2026-25083

GROWI OpenAI thread/message API endpoints do not perform authorization. Affected are v7.4.5 and earlier versions. A logged-in user who knows a shared AI assistant's identifier may view and/or tamper the other user's threads/messages...