PYSEC-2026-227

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index flashinfer.ai/whl/ using --extra-index-url, but the...

CVE-2026-47155

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image...

CVE-2026-54233

Affected software: vLLM (inference/serving engine). Vulnerability: decoding an audio file on the /v1/audio/transcriptions endpoint can cause extreme memory growth. A 25 MB OPUS upload decodes to about 14.9 GB of float32 PCM, because the audio decoder concatenates all frames in memory before retur...

CVE-2026-54235 vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, ll temperature validation gates use comparison operators , which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagat...

CVE-2026-53923 vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

vLLM is an inference and serving engine for large language models LLMs. From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels csrc/quantization/gguf/ggufkernel.cu causes partial tensor processing. The output tensor is allocated at full size via...

CVE-2026-49468 LiteLLM: Authentication Bypass via Host Header Injection

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

EUVD-2026-38332

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search...

Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection for Repository-Scale Codebases

Memory safety vulnerabilities remain a significant threat even for projects with extensive fuzzing and manual auditing. Recent results suggest that large language models hold great promise for detecting such vulnerabilities, but they are unreliable, at risk of hallucination, and challenging to...

CVE-2026-12045 pgAdmin 4: AI Assistant read-only transaction bypass allows unauthorised writes and remote code execution

Read-only transaction bypass in the pgAdmin 4 AI Assistant allows an attacker who can influence database content that the assistant reads to execute arbitrary SQL with the privileges of the pgAdmin user's database role. The AI Assistant's executesqlquery tool runs LLM-generated SQL inside a BEGIN...

PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters

Summary The email search tool in src/praisonai-agents/praisonaiagents/tools/emailtools.py constructs IMAP SEARCH commands by interpolating LLM-controlled parameters fromaddr, subject, query directly into IMAP protocol strings using f-string formatting with double-quote delimiters. An attacker who...

GHSA-C969-5X3P-VQ3V PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters

Summary The email search tool in src/praisonai-agents/praisonaiagents/tools/emailtools.py constructs IMAP SEARCH commands by interpolating LLM-controlled parameters fromaddr, subject, query directly into IMAP protocol strings using f-string formatting with double-quote delimiters. An attacker who...

GHSA-X8XR-MJ9X-6H7W Duplicate Advisory: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-8jr5-v98p-w75m. This link is maintained to preserve external references. Original Description A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from...

CVE-2026-12491

A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency tRNS data, during image processing. When images are converted to RGB, transparency informatio...

CVE-2026-53538 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-12.9, wazuh-manager-fips, airflow-core, litellm, airflow, wazuh-manager, airflow-postgres-fips...

ShellGames: Speculative LLM-Driven SSH Deception

Cyber deception and Moving Target Defense are promising strategies that aim to disrupt adversaries by increasing uncertainty. However, sustaining long-lived, credible interactive sessions with adversaries remains an open challenge. Large Language Models LLMs offer a promising path toward more...

PT-2026-57550

Name of the Vulnerable Software and Affected Versions Crawl4AI versions prior to 0.8.8 Description The Docker API server contains credential exfiltration flaws due to improper input validation and insecure configuration handling. Unauthenticated attackers can redirect LLM API calls to external...

SkillVetBench: LLM-As-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted. The gap we fill: existing scanners operate at the code layer and are structurally blind to instruction-layer...

Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?

We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model LLM security review is on the same JavaScript code, prompt, and benchmark harness. The headline result is that LLM security findings were unevenly repeatable: reference-matched findings were...

CVE-2026-46517

LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, hardcoded "trustremotecode=True" enables HF supply-chain RCE without user opt-in. At time of publication, there are no publicly available patches...

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross. Within this broader red-line scenario, autonomous penetration represents a core enabling capability and...