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]
3,710
[LAST_24H]
1
[LAST_7D]
1
Daily BriefingFriday, May 8, 2026
>

Critical RCE Vulnerabilities in LiteLLM Proxy Server: LiteLLM, a proxy server that forwards requests to AI model APIs, disclosed three critical and high-severity flaws in versions 1.74.2 through 1.83.6. Two test endpoints allowed attackers with valid API keys to execute arbitrary code (running any commands an attacker wants) on the server by submitting malicious configurations or prompt templates without sandboxing (CVE-2026-42271, CVE-2026-42203, both critical), while a SQL injection flaw (inserting malicious code into database queries) let unauthenticated attackers read or modify stored API credentials (CVE-2026-42208, high).

>

ClaudeBleed Exploit Allows Extension Hijacking in Chrome: Anthropic's Claude browser extension contains a vulnerability that allows malicious Chrome extensions to hijack it and perform unauthorized actions like exfiltrating files, sending emails, or stealing code from private repositories. The flaw stems from the extension trusting any script from claude.ai without verifying the actual caller, and while Anthropic released a partial fix in version 1.0.70 on May 6, researchers report it remains exploitable when the extension runs in privileged mode.

Latest Intel

page 322/371
VIEW ALL
01

CVE-2023-25664: TensorFlow is an open source platform for machine learning. Prior to versions 2.12.0 and 2.11.1, there is a heap buffer

security
Mar 25, 2023

TensorFlow, an open source machine learning platform, had a heap buffer overflow vulnerability (a memory safety bug where data is written beyond allocated space) in a function called TAvgPoolGrad before versions 2.12.0 and 2.11.1. This vulnerability could potentially allow attackers to crash the software or execute code.

>

AI Systems Show Triple the High-Risk Vulnerabilities of Legacy Software: Penetration testing data reveals that AI and LLM systems have 32% of findings rated high-risk compared to just 13% for traditional software, with only 38% of high-risk AI issues getting resolved. Security experts attribute this gap to rapid deployment without mature controls, novel attack surfaces like prompt injection (tricking AI by hiding instructions in input), and fragmented responsibility for remediation across teams.

>

Model Context Protocol Emerging as Critical Security Blind Spot: Model Context Protocol (MCP, a plugin system connecting AI agents to external tools) has become a major vulnerability vector as organizations fail to scan for or monitor MCP-related risks. Recent supply chain attacks, such as the postmark-mcp npm package that exfiltrated emails from 300 organizations, demonstrate how attackers exploit widely-trusted MCP packages and hardcoded credentials in AI configurations to enable credential theft and supply chain compromises at scale.

Fix: Update TensorFlow to version 2.12.0 or 2.11.1, which include the fix for this vulnerability.

NVD/CVE Database
02

CVE-2023-25663: TensorFlow is an open source platform for machine learning. Prior to versions 2.12.0 and 2.11.1, when `ctx->step_contain

security
Mar 25, 2023

TensorFlow, an open source machine learning platform, had a vulnerability in versions before 2.12.0 and 2.11.1 where a null pointer dereference (a crash caused by trying to use a memory location that doesn't exist) could occur in the Lookup function when a certain pointer was null. This weakness is classified as CWE-476 (NULL Pointer Dereference).

Fix: Update to TensorFlow version 2.12.0 or 2.11.1, which include the fix for this vulnerability. The patch is available at https://github.com/tensorflow/tensorflow/commit/239139d2ae6a81ae9ba499ad78b56d9b2931538a.

NVD/CVE Database
03

CVE-2023-25662: TensorFlow is an open source platform for machine learning. Versions prior to 2.12.0 and 2.11.1 are vulnerable to intege

security
Mar 25, 2023

TensorFlow, an open source machine learning platform, has a vulnerability in versions before 2.12.0 and 2.11.1 involving integer overflow (a math error where a number gets too large and wraps around) in the EditDistance function. This bug could potentially cause unexpected behavior or crashes in machine learning programs using affected versions.

Fix: Update TensorFlow to version 2.12.0 or version 2.11.1, both of which include a fix for this vulnerability.

NVD/CVE Database
04

CVE-2023-25660: TensorFlow is an open source platform for machine learning. Prior to versions 2.12.0 and 2.11.1, when the parameter `sum

security
Mar 25, 2023

TensorFlow, an open source platform for machine learning, has a bug in its `tf.raw_ops.Print` function that causes a seg fault (a crash where the program tries to access memory it shouldn't) when the `summarize` parameter is set to zero. The bug happens because the code tries to use a nullptr (a reference to nothing instead of valid data).

Fix: A fix is included in TensorFlow version 2.12.0 and version 2.11.1. Users should update to one of these versions or later.

NVD/CVE Database
05

CVE-2023-25659: TensorFlow is an open source platform for machine learning. Prior to versions 2.12.0 and 2.11.1, if the parameter `indic

security
Mar 25, 2023

TensorFlow, an open source machine learning platform, had a vulnerability where mismatched parameters in the `DynamicStitch` function could cause a stack OOB read (out-of-bounds read, where a program accesses memory it shouldn't). This flaw affected versions before 2.12.0 and 2.11.1.

Fix: Update TensorFlow to version 2.12.0 or version 2.11.1, which include the fix for this vulnerability.

NVD/CVE Database
06

CVE-2023-25658: TensorFlow is an open source platform for machine learning. Prior to versions 2.12.0 and 2.11.1, an out of bounds read i

security
Mar 25, 2023

TensorFlow, an open source platform for machine learning, had an out of bounds read vulnerability (a bug where code tries to access memory it shouldn't) in a component called GRUBlockCellGrad before versions 2.12.0 and 2.11.1. This vulnerability could potentially allow attackers to read sensitive data or crash the system.

Fix: Update TensorFlow to version 2.12.0 or version 2.11.1, which include the fix for this vulnerability.

NVD/CVE Database
07

CVE-2023-1177: Path Traversal: '\..\filename' in GitHub repository mlflow/mlflow prior to 2.2.1.

security
Mar 24, 2023

CVE-2023-1177 is a path traversal vulnerability (a flaw where an attacker can access files outside the intended directory by using special characters like '..') in MLflow versions before 2.2.1. This weakness allows attackers to potentially read or access files they shouldn't be able to reach on the system.

Fix: Update MLflow to version 2.2.1 or later. A patch is available at https://github.com/mlflow/mlflow/pull/7891/commits/7162a50c654792c21f3e4a160eb1a0e6a34f6e6e

NVD/CVE Database
08

CVE-2023-1176: Absolute Path Traversal in GitHub repository mlflow/mlflow prior to 2.2.2.

security
Mar 24, 2023

CVE-2023-1176 is an absolute path traversal vulnerability (a bug where an attacker can access files anywhere on a system by using file paths that start from the root directory) found in MLflow, an open-source platform for managing machine learning experiments, affecting versions before 2.2.2. The vulnerability was discovered and reported through the huntr.dev bug bounty program.

Fix: Fixed in version 2.2.2. A patch is available at https://github.com/mlflow/mlflow/commit/63ef72aa4334a6473ce7f889573c92fcae0b3c0d.

NVD/CVE Database
09

CVE-2023-27494: Streamlit, software for turning data scripts into web applications, had a cross-site scripting (XSS) vulnerability in ve

security
Mar 16, 2023

Streamlit, software that converts data scripts into web applications, had a cross-site scripting vulnerability (XSS, where an attacker injects malicious code that runs in a user's browser) in versions 0.63.0 through 0.80.0. An attacker could craft a malicious URL containing JavaScript code, trick a user into clicking it, and the Streamlit server would execute that code in the victim's browser.

Fix: Update to version 0.81.0, which contains a patch for this vulnerability.

NVD/CVE Database
10

Yolo: Natural Language to Shell Commands with ChatGPT API

industry
Mar 5, 2023

Yolo is a tool that uses ChatGPT API (OpenAI's language model accessed through code) to translate natural language questions into shell commands (the text-based interface for controlling a computer) that can be executed automatically. The tool helps users who forget command syntax by converting plain English requests into proper bash, zsh, or PowerShell commands, with a safety feature that shows the command before running it unless the user enables automatic execution.

Embrace The Red
Prev1...320321322323324...371Next