aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI Sec Watch

The security intelligence platform for AI teams

AI security threats move fast and get buried under hype and noise. Built by an Information Systems Security researcher to help security teams and developers stay ahead of vulnerabilities, privacy incidents, safety research, and policy developments.

Independent research. No sponsors, no paywalls, no conflicts of interest.

[TOTAL_TRACKED]
4,642
[LAST_24H]
4
[LAST_7D]
96
Daily BriefingSunday, June 14, 2026
>

Neural Network Robustness Testing Methods Surveyed: An academic review catalogs techniques for assessing whether image recognition systems maintain accuracy when confronted with adversarial inputs (deliberately crafted inputs designed to fool AI models) or unexpected conditions.

>

Generative AI Reshapes Ransomware Defense Calculus: Analysis argues that conventional defenses against ransomware (malicious software that encrypts files and demands payment) may prove inadequate as generative AI tools enable more sophisticated attacks and alter the threat landscape.

Latest Intel

page 407/465
VIEW ALL
01

Hacking Google Bard - From Prompt Injection to Data Exfiltration

securitysafety
Critical This Week5 issues
critical

CVE-2026-45833: A code injection vulnerability in version 0.4.17 or later of the ChromaDB Python project allows an authenticated attacke

CVE-2026-45833NVD/CVE DatabaseJun 12, 2026
Jun 12, 2026
Nov 3, 2023

Google Bard's new Extensions feature allows it to access personal data like YouTube videos, Google Drive files, Gmail, and Google Docs. Because Bard analyzes this untrusted data, it is vulnerable to indirect prompt injection (a technique where hidden instructions in documents trick an AI into performing unintended actions), which a researcher demonstrated by getting Bard to summarize videos and documents.

Embrace The Red
02

CVE-2023-46315: The zanllp sd-webui-infinite-image-browsing (aka Infinite Image Browsing) extension before 977815a for stable-diffusion-

security
Oct 22, 2023

The Infinite Image Browsing extension for Stable Diffusion web UI (a tool for generating images with AI) has a security flaw that allows attackers to read any file on a computer if Gradio authentication is enabled without a secret key configuration. Attackers can exploit this by manipulating URLs with /file?path= to access sensitive files, such as environment variables that might contain login credentials.

Fix: Update to commit 977815a or later. The patch is available at https://github.com/zanllp/sd-webui-infinite-image-browsing/pull/368/commits/977815a2b28ad953c10ef0114c365f698c4b8f19

NVD/CVE Database
03

CVE-2023-32786: In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrar

security
Oct 20, 2023

CVE-2023-32786 is a prompt injection vulnerability (tricking an AI by hiding instructions in its input) in Langchain version 0.0.155 and earlier that allows attackers to force the service to retrieve data from any URL they choose. This could lead to SSRF (server-side request forgery, where an attacker makes a server request data from unintended locations) and potentially inject harmful content into tasks that use the retrieved data.

NVD/CVE Database
04

Google Cloud Vertex AI - Data Exfiltration Vulnerability Fixed in Generative AI Studio

security
Oct 19, 2023

Google Cloud's Vertex AI Generative AI Studio had a data exfiltration vulnerability caused by image markdown injection (a technique where attackers embed hidden commands in image references to steal data). The vulnerability was responsibly disclosed to Google and has been fixed.

Embrace The Red
05

CVE-2023-46229: LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an e

security
Oct 19, 2023

LangChain versions before 0.0.317 have a vulnerability called SSRF (server-side request forgery, where an attacker tricks the application into making requests to unintended servers) in its recursive URL loader component. The flaw allows web crawling to move from an external server to an internal server that should not be accessible.

Fix: Update LangChain to version 0.0.317 or later. Patches are available at https://github.com/langchain-ai/langchain/commit/9ecb7240a480720ec9d739b3877a52f76098a2b8 and https://github.com/langchain-ai/langchain/pull/11925.

NVD/CVE Database
06

CVE-2023-45063: Cross-Site Request Forgery (CSRF) vulnerability in ReCorp AI Content Writing Assistant (Content Writer, GPT 3 & 4, ChatG

security
Oct 12, 2023

A CSRF vulnerability (cross-site request forgery, where an attacker tricks a user into performing unwanted actions on a website they're logged into) was found in the ReCorp AI Content Writing Assistant plugin for WordPress in versions 1.1.5 and earlier. This flaw could allow attackers to exploit users of the plugin without their knowledge.

NVD/CVE Database
07

CVE-2023-44467: langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-202

security
Oct 9, 2023

CVE-2023-44467 is a vulnerability in LangChain Experimental (a library for building AI applications) before version 0.0.306 that allows attackers to bypass a previous security fix and run arbitrary code (unauthorized commands) on a system using the __import__ function in Python, which the pal_chain/base.py file failed to block.

Fix: Upgrade LangChain to version 0.0.306 or later. A patch is available at https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483.

NVD/CVE Database
08

Microsoft Fixes Data Exfiltration Vulnerability in Azure AI Playground

security
Sep 29, 2023

LLM applications like chatbots are vulnerable to data exfiltration (unauthorized data theft) through image markdown injection, a technique where attackers embed hidden instructions in untrusted data to make the AI generate image tags that leak information. Microsoft patched this vulnerability in Azure AI Playground, though the source does not describe the specific technical details of their fix.

Embrace The Red
09

CVE-2023-43654: TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper

security
Sep 28, 2023

TorchServe (a tool for running PyTorch machine learning models as web services) has a vulnerability in its default configuration that fails to validate user inputs properly, allowing attackers to download files from any URL and save them to the server's disk. This could let attackers damage the system or steal sensitive information, affecting versions 0.1.0 through 0.8.1.

Fix: Upgrade to TorchServe release 0.8.2 or later, which includes a warning when the default value for allowed_urls is used. Users should also configure the allowed_urls setting and specify which model URLs are permitted.

NVD/CVE Database
10

Advanced Data Exfiltration Techniques with ChatGPT

security
Sep 28, 2023

An indirect prompt injection attack (tricking an AI into following hidden instructions in its input) can allow an attacker to steal chat data from ChatGPT users by either having the AI embed information into image URLs (image markdown injection, which embeds data into web links displayed as images) or convincing users to click malicious links. ChatGPT Plugins, which are add-ons that extend ChatGPT's functionality, create additional exfiltration risks because they have minimal security review before being deployed.

Embrace The Red
Prev1...405406407408409...465Next
critical

CVE-2026-46442: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, POST /a

CVE-2026-46442NVD/CVE DatabaseJun 8, 2026
Jun 8, 2026
high

CVE-2026-50287: AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a

CVE-2026-50287NVD/CVE DatabaseJun 12, 2026
Jun 12, 2026
high

CVE-2026-47138: Parse Server is an open source backend that can be deployed to any infrastructure that can run Node.js. Prior to version

CVE-2026-47138NVD/CVE DatabaseJun 12, 2026
Jun 12, 2026
high

Google Sues Chinese Smishing Network Accused of Using Gemini AI in Phishing

The Hacker NewsJun 12, 2026
Jun 12, 2026