From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting

As the role of Large Language Models LLM-based coding assistants in software development becomes more critical, so does the role of the bugs they generate in the overall cybersecurity landscape. While a number of LLM code security benchmarks have been proposed alongside approaches to improve the...

Malicious code in wayspiritmcp-tpa (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 523cbbda7a0fda2addfcd432b1bfcc1df072ee67a593ffce535b7da7005caae8 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...

Malicious code in wayspiritmcp-weather (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 c3dbe830c7b2364daef2e4634c16062b86b0b26b88f95533e9413aa91bc646fd Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...

Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback

Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I present a hybrid fuzzing framework that integrates static an...

CVE-2025-64318

Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Manipulating Writeable Configuration Files.This issue affects Mulesoft Anypoint Code Builder: before 1.12.1...

CVE-2025-10875

Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Code Injection.This issue affects Mulesoft Anypoint Code Builder: before 1.11.6...

CVE-2025-64318

Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Manipulating Writeable Configuration Files.This issue affects Mulesoft Anypoint Code Builder: before 1.12.1...

CVE-2025-10875

Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Code Injection.This issue affects Mulesoft Anypoint Code Builder: before 1.11.6...

Aether - Adaptive Exploit and Threat Hunting Engine for EVM-based Repositories

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and optionally validating those tests on mainnet forks. It combines static analysis, prompt-driven LLM analysis, and AI-ensemble...

PT-2025-45033

Name of the Vulnerable Software and Affected Versions Salesforce Agentforce Vibes Extension versions prior to 3.2.0 Description An issue exists in Salesforce Agentforce Vibes Extension related to improper neutralization of input used for LLM prompting, which can lead to code injection. The issue...

Scam Shield: Multi-Model Voting and Fine-Tuned LLMs against Adversarial Attacks

Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical Scam Detection System HSDS that combines a lightweight multi-model voting front end with a fine-tuned LLaMA 3.1 8B Instruct back end to improve accura...

LLM-Enabled Espionage : The AI assistant that moonlights as a mole

Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. It began as a low-priority alert from the SOC: an AI assistant accessed an internal finance folder at 2:14 AM. No credentials were stolen. No...

Network Intrusion Detection: Evolution from Conventional Approaches to LLM Collaboration and Emerging Risks

This survey systematizes the evolution of network intrusion detection systems NIDS, from conventional methods such as signature-based and neural network NN-based approaches to recent integrations with large language models LLMs. It clearly and concisely summarizes the current status, strengths, a...

Evaluating Large Language Models in Detecting Secrets in Android Apps

Mobile apps often embed authentication secrets, such as API keys, tokens, and client IDs, to integrate with cloud services. However, developers often hardcode these credentials into Android apps, exposing them to extraction through reverse engineering. Once compromised, adversaries can exploit...

The Attribution Story of WhisperGate: An Academic Perspective

This paper explores the challenges of cyberattack attribution, specifically APTs, applying the case study approach for the WhisperGate cyber operation of January 2022 executed by the Russian military intelligence service GRU and targeting Ukrainian government entities. The study provides a detail...

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Large Language Model LLM based agents integrated into web browsers often called agentic AI browsers offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions hidden in a webpage deceive the agent into unwanted actions...

ArtPerception: ASCII Art-Based Jailbreak on LLMs with Recognition Pre-Test

The integration of Large Language Models LLMs into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alignments, which primarily focus on semantic interpretation, leave LLMs vulnerable to attacks that use non-standard data...

EUVD-2025-32853

vLLM is an inference and serving engine for large language models LLMs. Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided A...

CVE-2025-59425 vLLM vulnerable to timing attack at bearer auth

vLLM is an inference and serving engine for large language models LLMs. Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided A...

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...