Lucene search
+L

1107 matches found

Packet Storm News
Packet Storm News
added 2025/10/13 12:0 a.m.8 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 12:0 a.m.27 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
Packet Storm News
Packet Storm News
added 2025/10/07 12:0 a.m.9 views

Towards Reliable and Practical LLM Security Evaluations Via Bayesian Modelling

Before adopting a new large language model LLM architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully comparable, relying on heuristic inputs or employing metrics that fai...

7.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/06 12:0 a.m.9 views

Imperceptible Jailbreaking against Large Language Models

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications e.g., non-semantic suffixes. In this paper, we introduce imperceptible jailbreaks that exploit a...

7.4AI score
SaveExploits0
NVD
NVD
added 2025/10/03 9:15 p.m.8 views

CVE-2025-59944

Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...

9.8CVSS0.00359EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2025/10/03 8:15 p.m.13 views

CVE-2025-59944 Cursor IDE: Sensitive File Overwrite Bypass is Possible

Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...

8CVSS0.00359EPSS
SaveExploits0References1
CVE
CVE
added 2025/10/03 8:15 p.m.52 views

CVE-2025-59944

Cursor IDE versions 1.6.23 and earlier are affected by a vulnerability in how sensitive files are protected (notably /.cursor/mcp.json). The issue arises from case-sensitive checks that can be bypassed, allowing an attacker to modify sensitive files via prompt injection and achieve remote code ex...

9.8CVSS7.8AI score0.00359EPSS
SaveExploits0References1Affected Software1
OSV
OSV
added 2025/10/03 8:15 p.m.6 views

CVE-2025-59944 Cursor IDE: Sensitive File Overwrite Bypass is Possible

Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...

8CVSS8.3AI score0.00359EPSS
SaveExploits0References3
EUVD
EUVD
added 2025/10/03 8:15 p.m.7 views

EUVD-2025-32373

Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...

8CVSS7.7AI score0.00359EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
added 2025/10/03 8:15 p.m.3 views

CVE-2025-59944 Cursor IDE: Sensitive File Overwrite Bypass is Possible

Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...

8CVSS7.8AI score0.00359EPSS
SaveExploits0References1
EUVD
EUVD
added 2025/10/03 8:7 p.m.6 views

EUVD-2024-46428

Malicious code in bioql PyPI...

9.1CVSS6.6AI score0.00541EPSS
SaveExploits0References1
EUVD
EUVD
added 2025/10/03 8:7 p.m.11 views

EUVD-2025-23407

Malicious code in bioql PyPI...

7.5CVSS6.6AI score0.00338EPSS
SaveExploits0References1
EUVD
EUVD
added 2025/10/03 8:7 p.m.10 views

EUVD-2025-26607

Malicious code in bioql PyPI...

7.6CVSS6.6AI score0.00312EPSS
SaveExploits0References2
EUVD
EUVD
added 2025/10/03 8:7 p.m.9 views

EUVD-2025-19434

Malicious code in bioql PyPI...

7.5CVSS6.5AI score0.00431EPSS
SaveExploits0References3
EUVD
EUVD
added 2025/10/03 8:7 p.m.6 views

EUVD-2024-48089

Malicious code in bioql PyPI...

6.4CVSS6.3AI score0.00359EPSS
SaveExploits0References1
EUVD
EUVD
added 2025/10/03 8:7 p.m.8 views

EUVD-2024-31893

Malicious code in bioql PyPI...

6.4CVSS6.3AI score0.00382EPSS
SaveExploits1References3
EUVD
EUVD
added 2025/10/03 8:7 p.m.11 views

EUVD-2025-23568

Malicious code in bioql PyPI...

9.8CVSS6.3AI score0.00294EPSS
SaveExploits0References1
EUVD
EUVD
added 2025/10/03 8:7 p.m.9 views

EUVD-2025-27052

Malicious code in bioql PyPI...

9.8CVSS6.5AI score0.00531EPSS
SaveExploits0References3
EUVD
EUVD
added 2025/10/03 8:7 p.m.9 views

EUVD-2025-10933

Malicious code in bioql PyPI...

9.3CVSS6.6AI score0.00609EPSS
SaveExploits0References2
EUVD
EUVD
added 2025/10/03 8:7 p.m.6 views

EUVD-2025-32227

Malicious code in bioql PyPI...

5.9CVSS6.6AI score0.00274EPSS
SaveExploits0References2
Rows per page
Query Builder