Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection

Large Language Models LLMs have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or function-level classification, failing to reflect the complexity of...

CoTDeceptor:Adversarial Code Obfuscation against CoT-Enhanced LLM Code Agents

LLM-based code agentse.g., ChatGPT Codex are increasingly deployed as detector for code review and security auditing tasks. Although CoT-enhanced LLM vulnerability detectors are believed to provide improved robustness against obfuscated malicious code, we find that their reasoning chains and...

CVE-2025-14148

IBM UCD - IBM DevOps Deploy 8.1 through 8.1.2.3 could allow an authenticated user with LLM integration configuration privileges to recover a previously saved LLM API Token...

CVE-2025-14148

IBM UCD - IBM DevOps Deploy 8.1 through 8.1.2.3 could allow an authenticated user with LLM integration configuration privileges to recover a previously saved LLM API Token...

CVE-2025-14148

CVE-2025-14148 affects IBM UCD - IBM DevOps Deploy versions 8.1 through 8.1.2.3. An authenticated user with LLM integration configuration privileges can recover a previously saved LLM API Token, exposing credentials. Root cause identified as insufficiently protected credentials (CWE-522). CVSSv3....

CVE-2025-14148 IBM DevOps Deploy is susceptible to a Insufficiently Protected Credentials vulnerability

IBM UCD - IBM DevOps Deploy 8.1 through 8.1.2.3 could allow an authenticated user with LLM integration configuration privileges to recover a previously saved LLM API Token...

PT-2025-51280

Name of the Vulnerable Software and Affected Versions IBM DevOps Deploy versions 8.1 through 8.1.2.3 Description An authenticated user with LLM integration configuration privileges may be able to recover a previously saved LLM API Token. Recommendations Update to a version later than 8.1.2.3...

Detecting Malicious Entra OAuth Apps with LLM-Based Permission Risk Scoring

This project presents a unified detection framework that constructs a complete corpus of Microsoft Graph permissions, generates consistent LLM-based risk scores, and integrates them into a real-time detection engine to identify malicious OAuth consent activity...

Security Bulletin: IBM DevOps Deploy is susceptible to a Insufficiently Protected Credentials vulnerability (CVE-2025-14148)

Summary IBM DevOps Deploy could allow an authenticated user with LLM integration configuration privileges to recover a previously saved LLM API Token. CVE-2025-14148 Vulnerability Details CVEID:CVE-2025-14148 DESCRIPTION: IBM DevOps Deploy could allow an authenticated user with LLM integration...

CVE-2025-63681

open-webui v0.6.33 is vulnerable to Incorrect Access Control. The API /api/tasks/stop/ directly accesses and cancels tasks without verifying user ownership, enabling attackers a normal user to stop arbitrary LLM response tasks...

CVE-2025-63681

open-webui v0.6.33 is vulnerable to Incorrect Access Control. The API /api/tasks/stop/ directly accesses and cancels tasks without verifying user ownership, enabling attackers a normal user to stop arbitrary LLM response tasks...

A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails Via Harmless Prompt Weaving and Adaptive Tree Search

Large language models LLMs remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional algorithmic search or recent agent-based workflows, the...

CacheTrap: Injecting Trojans in LLMs without Leaving Any Traces in Inputs or Weights

Adversarial weight perturbation has emerged as a concerning threat to LLMs that either use training privileges or system-level access to inject adversarial corruption in model weights. With the emergence of innovative defensive solutions that place system- and algorithm-level checks and correctio...

CVE-2025-62155

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to version 0.9.6, a recently patched SSRF vulnerability contains a bypass method that can bypass the existing security fix and still allow SSRF to occur. Because the existing fix only applie...

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries

LLM applications i.e., LLM apps leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While the increasing prevalence of LLM-powered applications provides users with unprecedented convenience, it also brings fort...

QLCoder: A Query Synthesizer for Static Analysis of Security Vulnerabilities

Static analysis tools provide a powerful means to detect security vulnerabilities by specifying queries that encode vulnerable code patterns. However, writing such queries is challenging and requires diverse expertise in security and program analysis. To address this challenge, we present QLCoder...

Malicious code in wei516-ppa (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 1d5a85017b397970606b9d2d5150a6f6ee8f71fdbd810fe6b0a8f34c577d76d1 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...

MAL-2025-191930 Malicious code in wei516-ppa (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 1d5a85017b397970606b9d2d5150a6f6ee8f71fdbd810fe6b0a8f34c577d76d1 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...

MAL-2025-191931 Malicious code in wei516-tpa (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 2ee2f69d608c9430677e3723e003b788f464ae688126d65199fc2936f1adfb0e 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 mcp-weather-full (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 c12eff5425b0aa04547b3bbff3444c1d96ca3cf765fdc105d7b7ff9252c9afda 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...