Security vulnerabilities, privacy incidents, safety concerns, and policy updates affecting LLMs and AI agents.
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability in its Python backend where an attacker could manipulate shared memory data to cause an out-of-bounds read (reading data from memory locations that should not be accessed). This vulnerability could potentially lead to information disclosure, meaning an attacker might be able to see sensitive data they shouldn't have access to.
NVIDIA Triton Inference Server (software that runs AI models on Windows and Linux) has a vulnerability where an attacker could send a specially crafted request that causes the server to try allocating an extremely large amount of memory, resulting in a crash (segmentation fault, which is when a program stops running due to a memory error). This could lead to a denial of service attack (making the service unavailable to legitimate users).
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability where an attacker could cause an integer overflow (a bug where a number becomes too large for the system to handle properly) by sending specially crafted inputs, potentially leading to denial of service (making the service unavailable) and data tampering. The severity rating from NIST has not yet been assigned.
NVIDIA Triton Inference Server (software that runs AI models on servers) for Windows and Linux has a vulnerability where an attacker could send specially crafted input that causes an integer overflow (when a number calculation exceeds the maximum value a computer can store, causing unexpected behavior), potentially leading to a denial of service attack (making the service unavailable to legitimate users).
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability where an attacker could send a specially crafted input that causes uncontrolled recursion (a function repeatedly calling itself without stopping), leading to a denial of service (DoS, making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though a full severity assessment from NIST has not yet been provided.
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability where an integer overflow or wraparound (a mistake in how the software handles very large numbers, causing them to wrap around to negative values) can occur when a user sends an invalid request, potentially causing a segmentation fault (a crash where the program tries to access memory it shouldn't). This could allow an attacker to cause a denial of service (making the service unavailable to legitimate users).
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability where an integer overflow or wraparound (a bug where a number gets too large and wraps around to a very small value) can occur when a user sends an invalid request, potentially causing a segmentation fault (a crash where the program tries to access memory it shouldn't) and leading to denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating (a 0-10 scale measuring how serious a vulnerability is).
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability where a double free (a memory error where the same memory location is freed twice) can occur when multiple requests cancel a stream before it gets processed, potentially causing a denial of service (making the service unavailable). The vulnerability is tracked as CVE-2025-23322.
NVIDIA Triton Inference Server (software that runs AI models on Windows and Linux computers) contains a vulnerability where a user can send a specially crafted invalid request that causes a divide by zero error (attempting to divide a number by zero, which crashes the system). This could allow an attacker to cause a denial of service attack (making the service unavailable to legitimate users).
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability in its Python backend where an attacker can send an extremely large request to exceed the shared memory limit (a pool of fast memory shared between processes), potentially exposing sensitive information. The vulnerability has a CVSS 4.0 severity rating, which measures how serious security flaws are on a scale of 0-10.
NVIDIA Triton Inference Server for Windows and Linux has a vulnerability in its Python backend where an attacker can send a specially crafted request to cause an out-of-bounds write (writing data outside the intended memory location). This could allow remote code execution (running malicious commands on the system), denial of service (making the system unavailable), data tampering (changing data), or information disclosure (exposing sensitive information).
CVE-2025-23318 is a vulnerability in NVIDIA Triton Inference Server (a tool that runs AI models for predictions) on Windows and Linux where an attacker could cause an out-of-bounds write (writing data outside the intended memory location) in the Python backend component. If successfully exploited, this could allow an attacker to execute code, crash the system, change data, or steal information.
NVIDIA Triton Inference Server has a vulnerability in its HTTP server (CVE-2025-23317) where an attacker could send a specially crafted HTTP request to start a reverse shell (a remote connection giving the attacker control of the system). This could allow remote code execution (running commands on a system without permission), denial of service (making the system unavailable), data tampering, or information disclosure.
NVIDIA Triton Inference Server has a vulnerability (CVE-2025-23311) where an attacker can send specially crafted HTTP requests to cause a stack overflow (a memory error where too much data is written to a limited storage area). This could allow remote code execution (running malicious commands on the server), denial of service (making the server unavailable), information disclosure (leaking data), or data tampering (modifying stored information).
NVIDIA Triton Inference Server (software that runs AI models for prediction tasks) for Windows and Linux has a vulnerability where attackers can send specially crafted inputs to cause a stack buffer overflow (writing data beyond allocated memory limits), potentially leading to remote code execution (running commands on the affected system), denial of service (making the system unavailable), information disclosure, and data tampering. The vulnerability has a CVSS score (severity rating) of 4.0.
A ReDoS vulnerability (regular expression denial of service, where a specially crafted input causes a regex pattern to consume excessive CPU) exists in Hugging Face Transformers library version 4.51.3 and earlier, in a function that converts TensorFlow model weight names to PyTorch format. An attacker can exploit this with malicious input strings to crash services or exhaust system resources.
LibreChat (a ChatGPT-like application) versions 0.0.6 through 0.7.7-rc1 have a vulnerability where an exposed testing endpoint called /api/search/test allows anyone to read chat messages from any user by directly accessing the Meilisearch engine (a search database) without proper permission checks. This is a serious security flaw because it exposes private conversations.
Claude Code is an agentic coding tool (software that can automatically write and execute code). In versions before 1.0.20, a flaw in how the tool parses commands allows attackers to skip the confirmation prompt that normally protects users before running untrusted code. Exploiting this requires the attacker to insert malicious content into Claude Code's input.
Claude Code, an agentic coding tool (software that can write and modify code automatically), has a path validation flaw in versions before 0.2.111 that allows attackers to bypass directory restrictions and access files outside the intended working directory. The vulnerability exploits prefix matching (checking if one string starts with another) instead of properly comparing full file paths, and requires the attacker to create a directory with the same prefix name and inject untrusted content into the tool's context.
Cursor, a code editor designed for AI-assisted programming, has a vulnerability in versions below 1.3.9 where it can write files in a workspace without asking the user for permission. An attacker can exploit this by using prompt injection (tricking the AI by hiding instructions in its input) to create sensitive configuration files like .cursor/mcp.json, potentially gaining RCE (remote code execution, where an attacker can run commands on a system they don't own) on the victim's computer without approval.
Fix: Update to version 4.53.0 or later, which fixes the vulnerability.
NVD/CVE DatabaseFix: This issue is fixed in version 0.7.7. Users should upgrade to version 0.7.7 or later.
NVD/CVE DatabaseFix: This is fixed in version 1.0.20. Users should update Claude Code to version 1.0.20 or later.
NVD/CVE DatabaseFix: Update Claude Code to version 0.2.111 or later, as this version contains the fix for the path validation flaw.
NVD/CVE DatabaseFix: Update Cursor to version 1.3.9 or later, where this vulnerability is fixed.
NVD/CVE Database