Lucene search
+L

1084 matches found

Cvelist
Cvelist
added 2025/08/22 12:0 a.m.14 views

CVE-2025-50733

NextChat contains a cross-site scripting XSS vulnerability in the HTMLPreview component of artifacts.tsx that allows attackers to execute arbitrary JavaScript code when HTML content is rendered in the AI chat interface. The vulnerability occurs because user-influenced HTML from AI responses is...

0.00202EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
added 2025/08/21 12:0 a.m.33 views

IPIGuard: a Novel Tool Dependency Graph-Based Defense against Indirect Prompt Injection in LLM Agents

Large language model LLM agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources e.g., fetching information from public websites, tool responses may contain...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/19 12:0 a.m.6 views

CCFC: Core and Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection

Jailbreak attacks pose a serious challenge to the safe deployment of large language models LLMs. We introduce CCFC Core & Core-Full-Core, a dual-track, prompt-level defense framework designed to mitigate LLMs' vulnerabilities from prompt injection and structure-aware jailbreak attacks. CCFC...

7.7AI score
SaveExploits0
Tenable Nessus
Tenable Nessus
added 2025/08/19 12:0 a.m.4 views

Linux Distros Unpatched Vulnerability : CVE-2024-3303

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior...

6.4CVSS6.6AI score0.00382EPSS
SaveExploits1References2
Packet Storm News
Packet Storm News
added 2025/08/16 12:0 a.m.6 views

Invitation Is All You Need! Promptware Attacks against LLM-Powered Assistants in Production Are Practical and Dangerous

The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware - maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of these applications. While prior research warned about a potential shift in the threat...

7AI score
SaveExploits0
CNVD
CNVD
added 2025/08/14 12:0 a.m.7 views

Microsoft GitHub Copilot Remote Code Execution Vulnerability

GitHub Copilot is an AI-driven code assistant developed by Microsoft, widely used in Visual Studio Code, Visual Studio and other development environments, providing intelligent code completion and generation services for millions of developers worldwide. Microsoft GitHub Copilot remote code...

7.8CVSS8.9AI score0.02568EPSS
SaveExploits2References1
GithubExploit
GithubExploit
added 2025/08/13 4:58 p.m.379 views

Exploit for Command Injection in Microsoft

💥 CVE-2025-53773 — Remote Code Execution in GitHub Copilot 💥...

7.8CVSS8.2AI score0.02568EPSS
SaveExploits2
CNNVD
CNNVD
added 2025/08/12 12:0 a.m.6 views

Microsoft GitHub Copilot and Visual Studio 命令注入漏洞

GitHub Copilot is an AI-driven code assistant developed by Microsoft, widely used in Visual Studio Code, Visual Studio and other development environments, providing intelligent code completion and generation services for millions of developers worldwide. Microsoft GitHub Copilot remote code...

7.8CVSS8.8AI score0.02568EPSS
SaveExploits2References1
Positive Technologies
Positive Technologies
added 2025/08/12 12:0 a.m.4 views

PT-2025-32853

Name of the Vulnerable Software and Affected Versions GitHub Copilot affected versions not specified Visual Studio 2022 versions prior to 17.14.12 Description Improper neutralization of special elements used in a command leads to a command injection issue in GitHub Copilot and Visual Studio. This...

7.8CVSS8.2AI score0.02568EPSS
SaveExploits2References63
HackRead
HackRead
added 2025/08/10 10:37 a.m.41 views

AgentFlayer 0-click exploit abuses ChatGPT Connectors to Steal 3rd-party app data

AgentFlayer is a critical vulnerability in ChatGPT Connectors. Learn how this zero-click attack uses indirect prompt injection to…...

7.6AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2025/08/07 12:31 a.m.16 views

CVE-2025-54135

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

9.8CVSS6.6AI score0.01708EPSS
SaveExploits0References1
Packet Storm News
Packet Storm News
added 2025/08/06 12:0 a.m.9 views

Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy

Large Language Models LLMs are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs may introduce critical vulnerabilities in these systems. Here, we explore the impact of prompt-injection attacks targeting consensus...

7AI score
SaveExploits0
NVD
NVD
added 2025/08/05 1:15 a.m.10 views

CVE-2025-54130

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

9.8CVSS0.00294EPSS
SaveExploits0References1
OSV
OSV
added 2025/08/05 12:12 a.m.6 views

CVE-2025-54130 Cursor Agent is vulnerable prompt injection via Editor Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

7.5CVSS7.4AI score0.00294EPSS
SaveExploits0References3
Vulnrichment
Vulnrichment
added 2025/08/05 12:12 a.m.2 views

CVE-2025-54130 Cursor Agent is vulnerable prompt injection via Editor Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

7.5CVSS7.3AI score0.00294EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2025/08/05 12:12 a.m.13 views

CVE-2025-54130 Cursor Agent is vulnerable prompt injection via Editor Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

7.5CVSS0.00294EPSS
SaveExploits0References1
CVE
CVE
added 2025/08/05 12:12 a.m.42 views

CVE-2025-54130

CVE-2025-54130 (Cursor) affects Cursor, a code editor with AI features. In versions

9.8CVSS6.7AI score0.00294EPSS
SaveExploits0References1Affected Software1
Vulnrichment
Vulnrichment
added 2025/08/05 12:11 a.m.6 views

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

8.5CVSS7.3AI score0.01708EPSS
SaveExploits0References1
OSV
OSV
added 2025/08/05 12:11 a.m.9 views

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

8.5CVSS7.4AI score0.01708EPSS
SaveExploits0References3
Cvelist
Cvelist
added 2025/08/05 12:11 a.m.26 views

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

8.5CVSS0.01708EPSS
SaveExploits0References1
Rows per page
Query Builder