CVE-2026-18774

A flaw has been found in NousResearch hermes-agent up to 0.16.0. This affects the function saveurlimage of the file agent/imagegenprovider.py of the component xAI Image Generation Provider. This manipulation causes server-side request forgery. The attack may be initiated remotely. The exploit has...

CVE-2026-18774: Server-Side Request Forgery (SSRF)

A flaw has been found in NousResearch hermes-agent up to 0.16.0. This affects the function saveurlimage of the file agent/imagegenprovider.py of the component xAI Image Generation Provider. This manipulation causes server-side request forgery. The attack may be initiated remotely. The exploit has...

PT-2026-67837

Name of the Vulnerable Software and Affected Versions Open WebUI versions 0.7.0 through 0.10.0 Description An authenticated user whose features.image generation permission has been revoked can still trigger image generation by sending a feature flag in a chat-completion request. The server fails ...

PT-2026-67921

Summary An authenticated user whose features.image generation permission has been revoked can still make the server generate images by sending the feature flag in a chat-completion request. The chat pipeline took the client-supplied features object at face value and never re-checked the permissio...

PT-2026-67754

Name of the Vulnerable Software and Affected Versions hermes-agent versions prior to 0.16.1 Description A flaw in the xAI Image Generation Provider component allows for remote server-side request forgery SSRF, a condition where an attacker can induce the server to make requests to an unintended...

TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models

Recent commercial image-generation models can generate high-quality images with readable text e.g., posters, infographics, and manuals, attracting considerable attention. Yet we first show that this same capability also introduces a previously unreported safety vulnerability: these systems may...

CVE-2026-59198 Pillow TGA RLE encoder can serialize up to ~57 KB of adjacent heap data into generated images

Pillow is a Python imaging library. From 5.2.0 until 12.3.0, Pillow's TGA RLE encoder reads past its packed row buffer when saving a mode 1 image with TGA RLE compression, allowing adjacent process heap bytes to be copied into the generated TGA file. This issue is fixed in version 12.3.0...

PYSEC-2026-2893 PPTAgent: Arbitrary File Write + Directory Creation via markdown_table_to_image

Summary The markdowntabletoimage tool accepts a caller-controlled path parameter and passes it directly to gethtmltableimage: python pptagent/mcpserver.py:127-143 def markdowntabletoimagemarkdowntable: str, path: str, css: str - str: """ Args: path str: The file path where the image will be saved...

A week in security (July 6 – July 12)

Last week on Malwarebytes Labs: This new Windows malware can take over your PC and wipe it clean How mule betting scams recruit ordinary people Two Chrome updates in two days fix critical vulnerabilities How World Cup crypto prediction sites take your money 6.9 million driver’s license numbers...

Turn off this Meta setting before someone generates AI images of you

Every consumer app has a settings menu that lets you make decisions about things like notifications or dark mode. Meta has just decided that anyone can generate AI images of you from your public Instagram account by typing your Instagram handle into a prompt. On July 7, Meta launched its AI image...

Meta's New AI Image Tool Lets Others Use Your Public Instagram Photos in AI Images

Meta has announced that its new artificial intelligence AI model Muse Image lets people use public Instagram posts and reels to generate AI content, and it's enabled by default. "You can also @-mention Instagram accounts in the Meta AI app to bring specific Instagram profiles right into your...

CVE-2026-59227: Missing Authorization

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.8.11 before 0.10.0, POST /api/v1/images/edit required only a verified account and did not enforce the global image-edit switch or the per-user image-generation permission, allowing a non-admin user to...

ChatGPT produced graphic violent images that shocked researchers

AI assistants like ChatGPT are supposed to be safe to use, with appropriate guardrails to stop people creating harmful content. However, a British AI security firm just figured out how to make ChatGPT produce explicit material. Mindgard, a company that tests AI engines for weaknesses, found that ...

ChatGPT produced graphic violent images that shocked researchers

AI assistants like ChatGPT are supposed to be safe to use, with appropriate guardrails to stop people creating harmful content. However, a British AI security firm just figured out how to make ChatGPT produce explicit material. Mindgard, a company that tests AI engines for weaknesses, found that ...

DRUPAL-CONTRIB-2026-053

This module enables you to use OpenAI as a provider for the AI module. The module doesn't sufficiently sanitize user-supplied URLs, leading to a Server-side request forgery SSRF vulnerability. This vulnerability is mitigated by the fact that an attacker must have the access to change the host url...

PT-2026-52166

Name of the Vulnerable Software and Affected Versions Drupal OpenAI Provider versions 0.0.0 through 1.1.1 Drupal OpenAI Provider versions 1.2.0 through 1.2.2 Description Insufficient sanitization of user-supplied URLs leads to a Server-Side Request Forgery SSRF, a flaw where an attacker can induc...

OpenAI Provider - Moderately critical - Server-side Request Forgery - SA-CONTRIB-2026-053

This module enables you to use OpenAI as a provider for the AI module. The module doesn't sufficiently sanitize user-supplied URLs, leading to a Server-side request forgery SSRF vulnerability. This vulnerability is mitigated by the fact that an attacker must have the access to change the host url...

Nuxt OG Image Code Execution

The vulnerability of the Open Graph Picture Generation module in the Nuxt OG Image framework for creating web applications and websites related to Nuxt.js is related to the lack of security measures for protecting the website structure. Exploiting this vulnerability allows a malicious actor to...

DNG File Generator for Security Testing Masked RGB Tables

This Python script is a research-oriented DNG Digital Negative file generator designed to build a specially crafted image file with controlled metadata structures for security testing of DNG processing engines...

Gardyn 安全漏洞

Gardyn is an indoor smart hydroponic cultivation device developed by the American company Gardyn. There is a security vulnerability in the Gardyn Cloud API, which stems from the development and testing of APIs for image generation functions...