aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDataset
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.

[TOTAL_TRACKED]
2,700
[LAST_24H]
26
[LAST_7D]
172
Daily BriefingTuesday, March 31, 2026
>

FastGPT Authentication Bypass Enables Server-Side Proxying: FastGPT versions before 4.14.9.5 have a critical vulnerability (CVE-2026-34162) where an HTTP testing endpoint lacks authentication and acts as an open proxy, letting unauthenticated attackers make requests on behalf of the FastGPT server. A separate high-severity SSRF vulnerability (CVE-2026-34163) in the same platform's MCP tools endpoints allows authenticated attackers to trick the server into scanning internal networks and accessing cloud metadata services.

>

Command Injection Flaws Hit MLflow and OpenAI Codex: MLflow's model serving feature has a high-severity command injection vulnerability (CVE-2026-0596) where attackers can insert shell commands through unsanitized model paths when `enable_mlserver=True`. Separately, researchers found a critical vulnerability in OpenAI Codex that could have allowed attackers to steal GitHub tokens (secret credentials for accessing repositories), which OpenAI has since patched.

Latest Intel

page 187/270
VIEW ALL
01

CVE-2024-52383: Missing Authorization vulnerability in KCT Ai Auto Tool Content Writing Assistant (Gemini Writer, ChatGPT ) All in One a

security
Nov 14, 2024

CVE-2024-52383 is a missing authorization vulnerability (a flaw where the software fails to check if a user has permission to perform an action) in the KCT Ai Auto Tool Content Writing Assistant plugin for WordPress, affecting versions up to 2.1.2. This vulnerability allows attackers to exploit incorrectly configured access control (permission settings) to gain unauthorized access.

Critical This Week5 issues
critical

CVE-2026-34162: FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, the FastGPT HTTP tools testing endpoint (/api/core/

CVE-2026-34162NVD/CVE DatabaseMar 31, 2026
Mar 31, 2026
>

Prompt Injection Bypasses Safety Controls in Multiple AI Tools: Multiple AI systems are vulnerable to prompt injection attacks (where attackers hide malicious instructions in input to trick the AI): the 1millionbot Millie chatbot (CVE-2026-4399) can be tricked using Boolean logic to bypass restrictions, Sixth's AI terminal tool (CVE-2026-30310) can be fooled into running dangerous commands without user approval, and CrewAI framework vulnerabilities allow attackers to chain exploits and escape sandboxes (restricted environments meant to contain AI actions).

>

Google Cloud Vertex AI Service Agents Had Excessive Default Permissions: Researchers found that AI agents running on Google Cloud's Vertex AI platform could be weaponized as "double agents" because the default service agent accounts (special accounts that run AI services) had excessive permissions, allowing attackers to steal credentials, access private code repositories, and reach internal infrastructure. Google responded by updating their documentation to better explain how Vertex AI uses resources and accounts.

NVD/CVE Database
02

CVE-2024-21799: Path traversal for some Intel(R) Extension for Transformers software before version 1.5 may allow an authenticated user

security
Nov 13, 2024

CVE-2024-21799 is a path traversal vulnerability (a bug where an attacker can access files outside intended directories) in Intel Extension for Transformers software versions before 1.5 that allows authenticated users (those with login access) to escalate their privileges through local access. The vulnerability has a CVSS score (severity rating) of 6.9, rated as medium severity.

Fix: Update Intel Extension for Transformers to version 1.5 or later.

NVD/CVE Database
03

OWASP Top 10 for Large Language Model Applications - 2023 - v1.1

securitypolicy
Nov 11, 2024

N/A -- The provided content is a GitHub navigation menu and marketing material, not a substantive article about the OWASP Top 10 for LLM Applications. No technical information, vulnerabilities, or security issues are described in the source text.

OWASP LLM Top 10
04

OWASP Top 10 for Large Language Model Applications - 2023 - v1

securitypolicy
Nov 11, 2024

N/A -- The provided content is a navigation menu and header from a GitHub webpage about enterprise features and developer tools. It does not contain substantive information about the OWASP Top 10 for Large Language Model Applications or any AI/LLM security issues.

OWASP LLM Top 10
05

Overview of all AI Act National Implementation Plans

policy
Nov 8, 2024

This document provides an overview of how different European Union countries are implementing the EU AI Act, which is legislation regulating artificial intelligence systems. Most countries show unclear or partial progress in establishing the required authorities (government bodies responsible for oversight and enforcement), with some nations like Denmark and Finland having made more concrete arrangements for coordinating market surveillance (monitoring that AI systems follow the rules) and serving as single points of contact.

EU AI Act Updates
06

CVE-2024-51751: Gradio is an open-source Python package designed to enable quick builds of a demo or web application. If File or UploadB

security
Nov 6, 2024

Gradio is an open-source Python package for building web applications, but versions before 5.5.0 have a vulnerability in the File and UploadButton components that allows attackers to read any files from the application server by exploiting path traversal (a technique where attackers use file paths like '../../../' to access files outside their intended directory). This happens when these components are used to preview file content.

Fix: Upgrade to Gradio release version 5.5.0 or later. The source explicitly states: 'This issue has been addressed in release version 5.5.0 and all users are advised to upgrade.'

NVD/CVE Database
07

CVE-2024-48061: langflow <=1.0.18 is vulnerable to Remote Code Execution (RCE) as any component provided the code functionality and the

security
Nov 4, 2024

Langflow version 1.0.18 and earlier has a remote code execution vulnerability (RCE, where an attacker can run commands on a system they don't own) because components with code functionality execute on the local machine instead of in a sandbox (an isolated environment that limits what code can access). This allows any component to potentially execute arbitrary code.

NVD/CVE Database
08

CVE-2024-48052: In gradio <=4.42.0, the gr.DownloadButton function has a hidden server-side request forgery (SSRF) vulnerability. The re

security
Nov 4, 2024

Gradio version 4.42.0 and earlier contain a server-side request forgery vulnerability (SSRF, a flaw where a server can be tricked into making requests to unintended targets) in the gr.DownloadButton function. The issue exists because the save_url_to_cache function doesn't validate URLs properly, allowing attackers to download local files and access sensitive information from the server.

NVD/CVE Database
09

CVE-2024-39722: An issue was discovered in Ollama before 0.1.46. It exposes which files exist on the server on which it is deployed via

security
Oct 31, 2024

Ollama before version 0.1.46 has a security flaw where attackers can use path traversal (a technique that manipulates file paths to access files outside their intended directory) in the api/push route to discover which files exist on the server. This allows an attacker to learn information about the server's file system that should be private.

Fix: Update Ollama to version 0.1.46 or later.

NVD/CVE Database
10

CVE-2024-39721: An issue was discovered in Ollama before 0.1.34. The CreateModelHandler function uses os.Open to read a file until compl

security
Oct 31, 2024

Ollama before version 0.1.34 has a vulnerability where the CreateModelHandler function improperly reads user-controlled file paths without limits, allowing an attacker to specify a blocking file like /dev/random, which causes a goroutine (a lightweight process in Go) to run infinitely and consume resources even after the user cancels their request. This is a resource exhaustion (CWE-404: Improper Resource Shutdown or Release) issue that can disrupt service availability.

Fix: Update Ollama to version 0.1.34 or later.

NVD/CVE Database
Prev1...185186187188189...270Next
critical

CVE-2025-15379: A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the `_

CVE-2025-15379NVD/CVE DatabaseMar 30, 2026
Mar 30, 2026
critical

CVE-2026-33873: Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assis

CVE-2026-33873NVD/CVE DatabaseMar 27, 2026
Mar 27, 2026
critical

Attackers exploit critical Langflow RCE within hours as CISA sounds alarm

CSO OnlineMar 27, 2026
Mar 27, 2026
critical

CVE-2025-53521: F5 BIG-IP Unspecified Vulnerability

CVE-2025-53521CISA Known Exploited VulnerabilitiesMar 26, 2026
Mar 26, 2026