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]
7,866
[LAST_24H]
2
[LAST_7D]
229
Daily BriefingSunday, September 27, 2026
>

Comprehensive Survey Maps AI Auditing Landscape: A new academic survey consolidates existing frameworks, principles, and methodologies used to audit AI systems for safety, fairness, and reliability, providing practitioners with a structured overview of current evaluation approaches.

Latest Intel

page 711/787
VIEW ALL
01

CVE-2024-6706: Attackers can craft a malicious prompt that coerces the language model into executing arbitrary JavaScript in the contex

security
Aug 7, 2024

CVE-2024-6706 is a vulnerability where attackers can write malicious prompts that trick a language model into running arbitrary JavaScript (code that executes in a web browser) on a webpage. This is a type of cross-site scripting (XSS) attack, where untrusted input is not properly cleaned before being displayed on a web page, allowing attackers to inject malicious code.

Critical This Week5 issues
critical

CVE-2026-84462: Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, a security filter that protects Zamm

CVE-2026-84462NVD/CVE DatabaseSep 25, 2026
Sep 25, 2026
NVD/CVE Database
02

CVE-2024-38206: An authenticated attacker can bypass Server-Side Request Forgery (SSRF) protection in Microsoft Copilot Studio to leak s

security
Aug 6, 2024

CVE-2024-38206 is a vulnerability in Microsoft Copilot Studio where an authenticated attacker (someone with valid login credentials) can bypass SSRF protection (security that prevents a server from being tricked into making unwanted network requests) to leak sensitive information over a network.

Fix: Patch available from Microsoft Corporation at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2024-38206

NVD/CVE Database
03

CVE-2024-6331: stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI

security
Aug 3, 2024

A vulnerability in the stitionai/devika AI project allows attackers to read sensitive files on a computer through prompt injection (tricking an AI by hiding malicious instructions in its input). The problem occurs because Google Gemini's safety filters were disabled, which normally prevent harmful outputs, leaving the system open to commands like reading `/etc/passwd` (a file containing user account information).

NVD/CVE Database
04

CVE-2024-38791: Server-Side Request Forgery (SSRF) vulnerability in Jordy Meow AI Engine: ChatGPT Chatbot allows Server Side Request For

security
Aug 1, 2024

CVE-2024-38791 is a server-side request forgery (SSRF, a flaw where an attacker tricks a server into making unwanted requests to other systems) vulnerability in the Jordy Meow AI Engine: ChatGPT Chatbot plugin that affects versions up to 2.4.7. The vulnerability allows attackers to exploit this weakness to perform unauthorized actions by manipulating the plugin's server requests.

NVD/CVE Database
05

CVE-2024-41950: Haystack is an end-to-end LLM framework that allows you to build applications powered by LLMs, Transformer models, vecto

security
Jul 31, 2024

Haystack is a framework for building applications with LLMs (large language models) and AI tools, but versions before 2.3.1 have a critical vulnerability where attackers can execute arbitrary code if they can create and render Jinja2 templates (template engines that generate dynamic text). This affects Haystack clients that allow users to create and run Pipelines, which are workflows that process data through multiple steps.

Fix: The vulnerability has been fixed in Haystack version 2.3.1. Users should upgrade to this version or later.

NVD/CVE Database
06

CVE-2023-33976: TensorFlow is an end-to-end open source platform for machine learning. `array_ops.upper_bound` causes a segfault when no

security
Jul 30, 2024

A bug in TensorFlow (an open source platform for building machine learning models) causes a segfault (a crash where the program tries to access memory it shouldn't) when the `array_ops.upper_bound` function receives input that is not a rank 2 tensor (a two-dimensional array of numbers).

Fix: The fix is included in TensorFlow 2.13 and has also been applied to TensorFlow 2.12 through a cherrypick commit (applying a specific code change to an older version).

NVD/CVE Database
07

CVE-2024-7297: Langflow versions prior to 1.0.13 suffer from a Privilege Escalation vulnerability, allowing a remote and low privileged

security
Jul 30, 2024

Langflow versions before 1.0.13 have a privilege escalation vulnerability (a security flaw where an attacker gains higher access rights than they should have) that lets a remote attacker with low privileges become a super admin by sending a specially crafted request to the '/api/v1/users' endpoint using mass assignment (a technique where an attacker modifies multiple fields at once by exploiting how the application handles user input).

Fix: Upgrade Langflow to version 1.0.13 or later.

NVD/CVE Database
08

Protect Your Copilots: Preventing Data Leaks in Copilot Studio

security
Jul 30, 2024

Microsoft's Copilot Studio is a low-code platform that lets employees build chatbots, but it has security risks including data leaks and unauthorized access when Copilots are misconfigured. The post warns that external attackers can find and interact with improperly set-up Copilots, and discusses how to protect organizational data using security controls.

Fix: Enable Data Loss Prevention (DLP, a security feature that prevents sensitive information from being shared), which is currently off by default in Copilot Studio.

Embrace The Red
09

CVE-2024-41120: streamlit-geospatial is a streamlit multipage app for geospatial applications. Prior to commit c4f81d9616d40c60584e36abb

security
Jul 26, 2024

CVE-2024-41120 is a vulnerability in streamlit-geospatial, a web application for geospatial data analysis, where user input to a URL field is not validated before being sent to a file-reading function. This allows attackers to make the server send requests to any destination they choose, a technique called SSRF (server-side request forgery, where an attacker tricks a server into making unwanted requests to other systems). The vulnerability affects code before a specific commit that patches the issue.

Fix: Commit c4f81d9616d40c60584e36abb15300853a66e489 fixes this issue. Users should update to the version containing this commit.

NVD/CVE Database
10

CVE-2024-41119: streamlit-geospatial is a streamlit multipage app for geospatial applications. Prior to commit c4f81d9616d40c60584e36abb

security
Jul 26, 2024

streamlit-geospatial is a web application for working with geographic data, but it has a critical vulnerability where user input is directly passed to the eval() function (a dangerous Python function that executes code), allowing attackers to run arbitrary code on the server. The vulnerability was fixed in commit c4f81d9616d40c60584e36abb15300853a66e489.

Fix: Update to commit c4f81d9616d40c60584e36abb15300853a66e489 or later, which fixes the vulnerability by removing the dangerous eval() call that accepted unsanitized user input.

NVD/CVE Database
Prev1...709710711712713...787Next
critical

GHSA-fm8p-53ww-hf6w: DBHub HTTP transport DNS rebinding allows unauthenticated browser-origin SQL execution

CVE-2026-61742GitHub Advisory DatabaseSep 24, 2026
Sep 24, 2026
critical

GHSA-g5f9-3xfg-p9mf: Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

CVE-2026-61732GitHub Advisory DatabaseSep 24, 2026
Sep 24, 2026
critical

CVE-2026-95985 - Kiro IDE Allows Agentic Writes to Global Configurations While Working in Untrusted Workspaces

AWS Security BulletinsSep 24, 2026
Sep 24, 2026
critical

Critical Bifrost AI Gateway Flaw Lets Attackers Run Commands Without Credentials

The Hacker NewsSep 22, 2026
Sep 22, 2026