623 matches found
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...
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...
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...
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 ...
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...
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:...
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:...
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:...
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:...
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...
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,...
Hybrid-Vulnerability-Analyzer
🛡️ Hybrid AI Vulnerability Analyzer & PoC/Exploit Generator A...
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...
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...
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...
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...
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...
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...
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...