Lucene search
+L

5411 matches found

EUVD
EUVD
•added 2025/10/14 12:24 p.m.•22 views

EUVD-2025-34181

A security issue exists within the x86 Microsoft Installer File MSI, installed with FTLinx. Authenticated attackers with valid Windows user credentials can initiate a repair and hijack the resulting console window. This allows the launching of a command prompt running with SYSTEM-level privileges...

8.5CVSS6.2AI score0.00182EPSS
SaveExploits0References2
EUVD
EUVD
•added 2025/10/14 12:23 p.m.•23 views

EUVD-2025-34183

A security issue exists within the Rockwell Automation Driver Package x64 Microsoft Installer File MSI repair functionality, installed with FTLinx. Authenticated attackers with valid Windows Users credentials can initiate a repair and hijack the resulting console window for vbpinstall.exe. This...

8.5CVSS6.3AI score0.00182EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2025/10/14 12:00 a.m.•22 views

PT-2025-41916

Name of the Vulnerable Software and Affected Versions FTLinx versions affected versions not specified Description A security issue exists in the x86 Microsoft Installer MSI used with FTLinx. Authenticated attackers with valid Windows user credentials can initiate a repair and hijack the resulting...

8.5CVSS6.2AI score0.00182EPSS
SaveExploits0References5
Packet Storm News
Packet Storm News
•added 2025/10/14 12:00 a.m.•15 views

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix

Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message, whereas most steganalysis methods attempt to detect the embedding in the image space. This paper proposes to perform steganalysis in the latent space by modeling the statistical...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2025/10/14 12:00 a.m.•71 views

PromptLocate: Localizing Prompt Injection Attacks

Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instructions and data. Localizing the injected prompt within contaminated data is...

7.2AI score
SaveExploits0
Positive Technologies
Positive Technologies
•added 2025/10/14 12:00 a.m.•19 views

PT-2025-41975

Name of the Vulnerable Software and Affected Versions Windsurft version 1.10.7 Description A prompt injection issue exists in Windsurft version 1.10.7 within Write mode when utilizing the SWE-1 model. By crafting a specific file name, it is possible to append instructions to the user prompt,...

4.6CVSS6.1AI score0.00191EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2025/10/14 12:00 a.m.•4 views

CVE-2025-36730: Undefined Security Weakness

A prompt injection vulnerability exists in Windsurft version 1.10.7 in Write mode using SWE-1 model. It is possible to create a file name that will be appended to the user prompt causing Windsurf to follow its instructions...

4.6CVSS5.8AI score0.00191EPSS
SaveExploits0References1
HackRead
HackRead
•added 2025/10/13 3:15 p.m.•32 views

OpenAI’s Guardrails Can Be Bypassed by Simple Prompt Injection Attack

Just weeks after its release, OpenAI’s Guardrails system was quickly bypassed by researchers. Read how simple prompt injection attacks fooled the system’s AI judges and exposed an ongoing security concern for OpenAI...

7.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2025/10/13 12:00 a.m.•14 views

Countermind: A Multi-Layered Security Architecture for Large Language Models

The security of Large Language Model LLM applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which rely on post hoc output filtering, are often brittle and fai...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2025/10/10 12:00 a.m.•47 views

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...

7.2AI score
SaveExploits0
RedhatCVE
RedhatCVE
•added 2025/10/09 1:27 p.m.•31 views

CVE-2025-11445

A vulnerability was detected in Kilo Code up to 4.86.0. Affected is the function ClineProvider of the file src/core/webview/ClineProvider.ts of the component Prompt Handler. Performing manipulation results in injection. The attack can be initiated remotely. The exploit is now public and may be...

7.5CVSS7AI score0.0032EPSS
SaveExploits0References1
OSV
OSV
•added 2025/10/08 9:15 a.m.•15 views

CVE-2025-11445

A vulnerability was detected in Kilo Code up to 4.86.0. Affected is the function ClineProvider of the file src/core/webview/ClineProvider.ts of the component Prompt Handler. Performing manipulation results in injection. The attack can be initiated remotely. The exploit is now public and may be...

5.3CVSS5.5AI score0.0032EPSS
SaveExploits0References6
NVD
NVD
•added 2025/10/08 9:15 a.m.•14 views

CVE-2025-11445

A vulnerability was detected in Kilo Code up to 4.86.0. Affected is the function ClineProvider of the file src/core/webview/ClineProvider.ts of the component Prompt Handler. Performing manipulation results in injection. The attack can be initiated remotely. The exploit is now public and may be...

7.5CVSS0.0032EPSS
SaveExploits0References6
Vulnrichment
Vulnrichment
•added 2025/10/08 8:32 a.m.•6 views

CVE-2025-11445 Kilo Code Prompt ClineProvider.ts ClineProvider injection

A vulnerability was detected in Kilo Code up to 4.86.0. Affected is the function ClineProvider of the file src/core/webview/ClineProvider.ts of the component Prompt Handler. Performing manipulation results in injection. The attack can be initiated remotely. The exploit is now public and may be...

7.5CVSS6.1AI score0.0032EPSS
SaveExploits0References6
Cvelist
Cvelist
•added 2025/10/08 8:32 a.m.•28 views

CVE-2025-11445 Kilo Code Prompt ClineProvider.ts ClineProvider injection

A vulnerability was detected in Kilo Code up to 4.86.0. Affected is the function ClineProvider of the file src/core/webview/ClineProvider.ts of the component Prompt Handler. Performing manipulation results in injection. The attack can be initiated remotely. The exploit is now public and may be...

7.5CVSS0.0032EPSS
SaveExploits0References6
CVE
CVE
•added 2025/10/08 8:32 a.m.•35 views

CVE-2025-11445

Kilo Code up to 4.86.0 is affected by an injection vulnerability in the ClineProvider function of src/core/webview/ClineProvider.ts within the Prompt Handler component. The issue allows remote manipulation and has publicly disclosed exploits; remediation is to apply the patch. The available docum...

7.5CVSS6.1AI score0.0032EPSS
SaveExploits0References6
Positive Technologies
Positive Technologies
•added 2025/10/08 12:00 a.m.•20 views

PT-2025-41241

Name of the Vulnerable Software and Affected Versions Kilo Code versions prior to 4.86.0 Description A flaw exists in Kilo Code that allows for injection through manipulation of the ClineProvider function within the src/core/webview/ClineProvider.ts file of the Prompt Handler component. This issu...

7.5CVSS6.4AI score0.0032EPSS
SaveExploits0References11
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2025/10/08 12:00 a.m.•3 views

CVE-2025-11445: Improper Neutralization of Special Elements in Output Used by a Downstream Component

A vulnerability was detected in Kilo Code up to 4.86.0. Affected is the function ClineProvider of the file src/core/webview/ClineProvider.ts of the component Prompt Handler. Performing manipulation results in injection. The attack can be initiated remotely. The exploit is now public and may be...

7.5CVSS5.2AI score0.0032EPSS
SaveExploits0References1
CNNVD
CNNVD
•added 2025/10/08 12:00 a.m.•17 views

Kilo Code 安全漏洞

Kilo Code is an AI coding assistant open-sourced by Kilo Code. A security vulnerability exists in Kilo Code 4.86.0 and earlier versions, which stems from improper manipulation of the ClineProvider function in the Prompt Handler component, which could lead to an injection attack...

7.5CVSS6.6AI score0.0032EPSS
SaveExploits0References6
EUVD
EUVD
•added 2025/10/07 12:30 a.m.•11 views

EUVD-2017-16758

Malware in sbrugna...

7.5CVSS7.5AI score0.1412EPSS
SaveExploits5References10
Rows per page
Query Builder