Lucene search
+L

623 matches found

OSV
OSV
added 2026/03/24 8:23 p.m.9 views

CVE-2025-33247

NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...

7.8CVSS7.4AI score
SaveExploits0References4
Packet Storm News
Packet Storm News
added 2026/03/24 12:0 a.m.16 views

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models Via Hierarchical Strategy Exploration

The rapid advancement of Vision-Language Models VLMs has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/24 12:0 a.m.16 views

Agent Audit: A Security Analysis System for LLM Agent Applications

What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the surrounding software stack: tool functions that pass untrusted...

5.9AI score
SaveExploits0
Positive Technologies
Positive Technologies
added 2026/03/23 12:0 a.m.10 views

PT-2026-27198

Name of the Vulnerable Software and Affected Versions New API versions 0.10.0 and later Description A flaw exists in the universal secure verification flow, allowing an authenticated user with a registered passkey to bypass the WebAuthn assertion requirement. This issue affects actions protected ...

4.9CVSS5.8AI score0.00289EPSS
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/23 12:0 a.m.43 views

AI in Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes

Large language models are rapidly changing how learners acquire and demonstrate cybersecurity skills. However, when human--AI collaboration is allowed, educators still lack validated competition designs and evaluation practices that remain fair and evidence-based. This paper presents a...

5.8AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/03/20 9:3 p.m.12 views

Malicious code in mangrove-sdk (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 d6714958f20775c2347e9c8b606d1de2e28ed29fe4b1a82261ca4fb966fc20fa During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

6AI score
SaveExploits0References1
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/03/20 8:54 p.m.12 views

Malicious code in efghr-honeybee-sdk (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 e77e2d0088390e5dc421f70a65ade331bfbf554afcc9cc42362098d0ed130692 During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

6AI score
SaveExploits0References1
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/03/20 8:49 p.m.13 views

Malicious code in flyio-token-client-efgh (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 2b09830263d8a35450ca657294a1725c441f2f7fe49cc7946e261e8f18401464 During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

6AI score
SaveExploits0References1
OSV
OSV
added 2026/03/20 8:49 p.m.9 views

MAL-2026-2004 Malicious code in flyio-token-client-efgh (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 2b09830263d8a35450ca657294a1725c441f2f7fe49cc7946e261e8f18401464 During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

6AI score
SaveExploits0References1
CNNVD
CNNVD
added 2026/03/20 12:0 a.m.17 views

Discourse 安全漏洞

Discourse is an open-source community discussion platform developed by Discourse. This platform includes features such as communities, email communication, and chat rooms. Versions of Discourse prior to 2026.3.0-latest.1, as well as versions before 2026.2.1 and 2026.1.2, have security...

5.3CVSS5.8AI score0.00211EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/03/19 8:55 p.m.18 views

EUVD-2026-13210

SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology,...

8.6CVSS6AI score0.00562EPSS
SaveExploits1References2
GithubExploit
GithubExploit
added 2026/03/14 2:42 p.m.173 views

Hybrid-Vulnerability-Analyzer

🛡️ Hybrid AI Vulnerability Analyzer & PoC/Exploit Generator A...

6.3AI score
SaveExploits0
OSV
OSV
added 2026/03/13 8:14 p.m.13 views

CVE-2026-32626 AnythingLLM has a Streaming Phase XSS to RCE via LLM Response Injection

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, AnythingLLM Desktop contains a Streaming Phase XSS vulnerability in the chat rendering pipeline that escalates to Remote Code Execution on the host OS...

9.6CVSS5.9AI score
SaveExploits0References4
SUSE CVE
SUSE CVE
added 2026/03/13 1:16 p.m.14 views

SUSE CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS5.9AI score0.00177EPSS
SaveExploits1References3
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/03/12 6:9 p.m.13 views

Malicious code in spectral-corsair-my-backdoor (npm)

Malicious package detected. Suspicious preinstall script exfiltrates data to a remote server. Multiple YARA rules and LLM analysis confirm. --- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0826a28f7948e68cdddd6260a01c3653a7f04deb2c9368054243ed47713ee353 The packa...

5.8AI score
SaveExploits0References3
OSV
OSV
added 2026/03/12 6:9 p.m.11 views

MAL-2026-1374 Malicious code in spectral-corsair-my-backdoor (npm)

Malicious package detected. Suspicious preinstall script exfiltrates data to a remote server. Multiple YARA rules and LLM analysis confirm. --- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0826a28f7948e68cdddd6260a01c3653a7f04deb2c9368054243ed47713ee353 The packa...

5.8AI score
SaveExploits0References3
Microsoft Secure
Microsoft Secure
added 2026/03/12 2:0 p.m.16 views

Detecting and analyzing prompt abuse in AI tools

This second post in our AI Application Security series is all about moving from planning to practice. AI Application Series 1: Security considerations when adopting AI tools established how AI adoption expands the attack surface and our threat-modelling guidance on the Microsoft security blog...

5.8AI score
SaveExploits0
OSV
OSV
added 2026/03/11 4:33 p.m.13 views

DRUPAL-CONTRIB-2026-028

The module and certain submodules AI Automators, AI Translate, AI API Explorer, AI Content Suggestions provide the ability to use an LLM to generate HTML or Markdown and preview it in a browser. Under certain circumstances, rendering of this HTML can lead to exposing secret communications in the...

7.5CVSS5.8AI score0.00232EPSS
SaveExploits0References1
Packet Storm News
Packet Storm News
added 2026/03/11 12:0 a.m.15 views

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents Via Causal Attribution of Tool Invocations

LLM agents are highly vulnerable to Indirect Prompt Injection IPI, where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination problem, which often fails to generalize to unseen payloads. We...

5.8AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/03/10 10:43 p.m.269 views

rami-kali-MCP

Red Team MCP Server MCP Model Context Protocol server that...

6AI score
SaveExploits0
Rows per page
Query Builder