LLM 安全漏洞

LLM is a multi-model large language model command-line interaction tool developed by Simon Willison. Versions of LLM 0.27.1 and earlier contain security vulnerabilities. These vulnerabilities stem from the use of the --functions command-line parameter to directly execute unsafe code using the exe...

GHSA-P58C-Q354-6C4F pgAdmin 4 contains local file inclusion (LFI) and server-side request forgery (SSRF) vulnerabilities

Local file inclusion LFI and server-side request forgery SSRF vulnerabilities in pgAdmin 4 LLM API configuration endpoints. User-supplied apikeyfile and apiurl preferences were passed to the LLM provider clients without validation. An authenticated user could read arbitrary server-side files by...

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache, batching, prefix sharing, speculative decoding, adapters,...

Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...

EUVD-2026-28647

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

CVE-2026-41487 Langfuse: Improper role-based-access control in Langfuse LLM connection management allowed users of role “member” to retrieve stored LLM provider API keys

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code Via Prompt Optimization

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure production code with relevant weaknesses to avoid in context, we...

Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows

GitHub Continuous Integration CI workflows increasingly integrate Large Language Models LLMs to automate review, triage, content generation, and repository maintenance. This creates a new attack surface: externally controllable workflow inputs can shape LLM prompts and outputs, which may in turn...

GHSA-89G2-XW5C-V95P PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

Summary This vulnerability has been fixed in https://github.com/icip-cas/PPTAgent/commit/418491a9a1c02d9d93194b5973bb58df35cf9d00. CodeExecutor.executeactions pptagent/apis.py:126-205 processes LLM-generated slide editing actions using Python's eval: python pptagent/apis.py:184-186 partialfunc =...

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts

Smart contracts on blockchains are prone to diverse security vulnerabilities that can lead to significant financial losses due to their immutable nature. Existing detection approaches often lack flexibility across vulnerability types and rely heavily on manually crafted expert rules. In this pape...

CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

QASecClaw: A Multi-Agent LLM Approach for False Positive Reduction in Static Application Security Testing

Static Application Security Testing tools help developers find security vulnerabilities before release, but they often produce many false positives. This increases manual review effort, reduces developer trust, and may cause real vulnerabilities to be ignored among noisy reports. We present...

Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems

The adoption of Internet of Things IoT systems at the network edge of smart architectures is increasing rapidly, intensifying the need for security mechanisms that are both adaptive and resource-efficient. In such environments, runtime defence mechanisms are no longer limited to detection alone b...

CVE-2026-42208

A flaw was found in LiteLLM. A database query used for proxy API key checks incorrectly incorporated caller-supplied key values directly into the query. This vulnerability allows an unauthenticated attacker to send a specially crafted Authorization header to any Large Language Model LLM API route...

MARD: A Multi-Agent Framework for Robust Android Malware Detection

With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep semantic understanding and interpretability of decisions. Although Large Language Models LLMs...

Large Language Models As Explainable Cyberattack Detectors for Energy Industrial Control Systems

In modern energy systems, industrial control systems ICS and power-system SCADA require intrusion detection that is not only accurate but also auditable by operators. The ICS intrusion-detection landscape is currently dominated by established supervised detectors. In this paper, we study whether ...

Dynamic Cyber Ranges

As LLM-driven agents advance in cybersecurity, Jeopardy CTF benchmarks are approaching saturation and cyber ranges, the natural next evaluation frontier, offer diminishing resistance under their current static design. We validate this observation by deploying an LLM-driven Advanced Persistent...

CVE-2026-7021

A weakness has been identified in SmythOS sre up to 0.0.15. This impacts an unknown function of the file packages/sdk/src/LLM/utils.ts of the component Connector Service. This manipulation of the argument baseURL causes information disclosure. It is possible to initiate the attack remotely. The...

Semantic Denial of Service in LLM-Controlled Robots

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases 1-5 tokens into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt...

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Emerging AR-LLM-based Social Engineering attack e.g., SEAR is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR Augmented Reality glass to capture the image and vocal information of the target, using the LLM to identify the targe...