Lucene search
+L

1085 matches found

Malwarebytes
Malwarebytes
added 2026/01/15 1:16 p.m.24 views

“Reprompt” attack lets attackers steal data from Microsoft Copilot

Researchers found a method to steal data which bypasses Microsoft Copilot's built-in safety mechanisms. The attack flow, called Reprompt , abuses how Microsoft Copilot handled URL parameters in order to hijack a user’s existing Copilot Personal session. Copilot is an AI assistant which connects t...

7.2AI score
SaveExploits0
The Hacker News
The Hacker News
added 2026/01/15 11:55 a.m.13 views

Model Security Is the Wrong Frame – The Real Risk Is Workflow Security

As AI copilots and assistants become embedded in daily work, security teams are still focused on protecting the models themselves. But recent incidents suggest the bigger risk lies elsewhere: in the workflows that surround those models. Two Chrome extensions posing as AI helpers were recently...

6.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/01/15 12:0 a.m.23 views

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a...

7.5AI score
SaveExploits0
NVD
NVD
added 2026/01/14 5:16 p.m.13 views

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

9.8CVSS0.00537EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2026/01/14 4:43 p.m.31 views

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

9.2CVSS0.00537EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
added 2026/01/14 4:43 p.m.15 views

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

9.2CVSS7AI score0.00537EPSS
SaveExploits0References1
ATTACKERKB
ATTACKERKB
added 2026/01/14 4:43 p.m.6 views

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

9.8CVSS5.7AI score0.00537EPSS
SaveExploits0References2Affected Software1
EUVD
EUVD
added 2026/01/14 4:43 p.m.12 views

EUVD-2026-2678

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

9.2CVSS6.8AI score0.00537EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
added 2026/01/14 12:0 a.m.19 views

PT-2026-2918

Name of the Vulnerable Software and Affected Versions Cursor versions prior to 2.3 Description Cursor is a code editor designed for programming with AI. When the Cursor Agent operates in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can be executed without appearing on the...

9.8CVSS6.7AI score0.00537EPSS
SaveExploits0References16
CNNVD
CNNVD
added 2026/01/14 12:0 a.m.10 views

Cursor 安全漏洞

Cursor is a Cursor open source intelligent code editor with deep AI integration. A security vulnerability exists in versions prior to Cursor 2.3 that stems from the fact that in autorun mode, certain shell built-in commands can be executed without being whitelisted and without the need for user...

9.8CVSS7.1AI score0.00537EPSS
SaveExploits0References2
RedhatCVE
RedhatCVE
added 2026/01/13 11:5 p.m.8 views

CVE-2024-58340

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

8.7CVSS6.7AI score0.0041EPSS
SaveExploits1References7
PyPA
PyPA
added 2026/01/12 11:15 p.m.18 views

PYSEC-2026-75

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

8.7CVSS6AI score0.0041EPSS
SaveExploits1References4Affected Software1
CVE
CVE
added 2026/01/12 11:5 p.m.29 views

CVE-2024-58340

LangChain

8.7CVSS6.7AI score0.0041EPSS
SaveExploits1References4Affected Software1
OSV
OSV
added 2026/01/12 11:5 p.m.6 views

CVE-2024-58340 LangChain <= 0.3.1 MRKLOutputParser ReDoS

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

8.7CVSS6.1AI score0.0041EPSS
SaveExploits1References6
Packet Storm News
Packet Storm News
added 2025/12/29 12:0 a.m.24 views

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models LLMs, Vision-Language Models VLMs, and new agentic AI systems, like LangChain and GraphChain. Nevertheless, this agentic environment increases the...

7.5AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/12/26 9:27 a.m.10 views

Critical LangChain Core Vulnerability Exposes Secrets via Serialization Injection

A critical security flaw has been disclosed in LangChain Core that could be exploited by an attacker to steal sensitive secrets and even influence large language model LLM responses through prompt injection. LangChain Core i.e., langchain-core is a core Python package that's part of the LangChain...

9.3CVSS7.8AI score0.41454EPSS
SaveExploits5
HackRead
HackRead
added 2025/12/24 11:23 a.m.16 views

Eurostar Accused Researchers of Blackmail for Reporting AI Chatbot Flaws

Researchers discovered critical flaws in Eurostar’s AI chatbot including prompt injection, HTML injection, guardrail bypass, and unverified chat IDs - Eurostar later accused them of blackmail...

7AI score
SaveExploits0
Wallarm Lab
Wallarm Lab
added 2025/12/23 7:55 a.m.14 views

From Agent2Agent Prompt Injection to Runtime Self-Defense: How Wallarm Redefines Agentic AI Security

Is an AI-to-AI attack scenario a science fiction possibility only for blockbusters like the Terminator series of movies? Well, maybe not! Researchers recently discovered that one AI agent can “inject malicious instructions into a conversation, hiding them among otherwise benign client requests an...

6.9AI score
SaveExploits0
OpenVAS
OpenVAS
added 2025/12/22 12:0 a.m.27 views

Moodle Prompt Injection Vulnerability (MSA-25-0053)

Moodle is prone to a prompt injection vulnerability. SPDX-FileCopyrightText: 2025 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only CPE = "cpe:/a:moodle:moodle"; ifdescriptio...

7.3CVSS5.4AI score0.00232EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/12/20 12:12 a.m.15 views

CVE-2025-63665

An issue in GT Edge AI Community Edition Versions before v2.0.12 allows attackers to execute arbitrary code via injecting a crafted JSON payload into the Prompt window...

9.8CVSS7.8AI score0.00436EPSS
SaveExploits0References1
Rows per page
Query Builder