CVE-2026-58473

CVE-2026-58473 (Cognee) vulnerability affects Cognee prior to 1.2.0. An improper access-control flaw allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which lacks admin/superuser checks. This enabl...

GO-2026-5925 Suspended Coder users retain access to AI Bridge LLM proxy endpoints in github.com/coder/coder

Suspended Coder users retain access to AI Bridge LLM proxy endpoints in github.com/coder/coder...

CVE-2026-55574

CVE-2026-55574 affects vLLM prior to 0.24.0, where structured_outputs.regex passes an unguarded user-supplied regex to grammar backends (xgrammar and outlines). In xgrammar, the string reaches the regex compiler without a timeout guard; in outlines, validation overlooks regex complexity (e.g., ne...

CVE-2026-44934

A information disclosure when DEBUG loglevel is set in SUSE Rancher AI Agent 1.0 before 1.0.2 could leak API keys or LLM response text with potential sensitive data into logfiles, allowing local attackers to misuse respective gained data or credentials...

PT-2026-55978

Name of the Vulnerable Software and Affected Versions vLLM versions 0.22.0 through 0.23.0 Description The software fails to validate the size of uploaded audio files before loading them into memory. Specifically, the endpoints '/v1/audio/transcriptions' and '/v1/audio/translations' execute the...

282 iOS AI Apps Leak API Keys and Open AI Proxy Access in Network Traffic Study

Researchers tested 444 AI chatbot apps for iPhone and found that 282 of them, nearly two-thirds, exposed paid AI access through their network traffic. In many cases, the path in was visible just by watching what the app sent: a plaintext API key, a reusable token, or a backend server that accepte...

CVE-2026-54235

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The temperature validation gates, which use comparison operators, incorrectly handle Not-a-Number NaN and positive Infinity values in Python's IEEE 754 float semantics. These invalid values can bypass...

CVE-2026-45792 RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM

rtk filters and compresses command outputs before they reach your LLM context. Prior to 0.32.0, RTK Rust Token Killer improperly trusts project-local configuration files. RTK automatically loads .rtk/filters.toml from the working directory with highest priority and without user notification. An...

CVE-2026-54235

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-2026-47155

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...

Mind Your Key: An Empirical Study of LLM API Credential Leakage in IOS Apps

The rapid integration of large language models LLMs into mobile applications has introduced a new class of credential security risk: leaked credentials that grant unauthorized access to LLM inference services, causing financial damage to developers. Prior work on credential leakage has focused...

EUVD-2026-35116

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, evaluation create and update mass-assignment allows cross-workspace evaluation takeover. This issue has been patched in version 3.1.2...

EUVD-2026-35113

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, CustomTemplate create and update mass-assignment allows cross-workspace template takeover. This issue has been patched in version 3.1.2...

Steganography without Modification: Hidden Communication Via LLM Seeds

We demonstrate that widely deployed Large Language Model LLM inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generato...

RECON: An LLM-Enhanced Backward Constraint Analysis Framework

While traditional techniques, such as symbolic execution, provide a principled foundation for precise constraint reasoning in program analysis, they struggle to scale to modern software systems mainly due to path explosion, the need for function modeling, and the loss of semantic intent at...

POISE: Position-Aware Undetectable Skill Injection on LLM Agents

Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A practically dangerous injection must stay invisible: if executing the payload derails the user's legitimate task, the resulting failure signal invite...

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memory poisoning, where a single adversarial memory write can exert long-term influence over agent behavior. We present a...