ASR AI Security Radar
Back to homepage

Recent AI Security Incidents

This archive includes all published incident pages. Page 17 of 18.

Each page is intended to help a security team answer three questions quickly: why the issue is AI-relevant, what part of the workflow may be exposed, and what actions should happen first.

Selection criteria and correction policy are documented in Methodology & Editorial Policy.

AI security incident: VU#271649: Stack-based buffer overflow in libtasn1 versions v4.20.0 and earlier

Incident date: January 20, 2026 | Published: February 25, 2026

Overview A stack-based buffer overflow vulnerability exists in GNU libtasn1, a low-level ASN.1 parsing library. The issue is caused by unsafe string concatenation in the asn1_expand_octet_string function located in decoding.c .

Read details

AI security incident: VU#818729: Safetica contains a kernel driver vulnerability

Incident date: January 20, 2026 | Published: February 25, 2026

Overview Kernel driver ProcessMonitorDriver.sys in Safetica's endpoint client x64, versions 10.5.75.0 and 11.11.4.0, allows for an unprivileged user to abuse an IOCTL path and terminate protected system processes.

Read details

AI security incident: VU#244846: Server-Side Template Injection (SSTI) vulnerability exist in Genshi

Incident date: January 20, 2026 | Published: February 25, 2026

Overview A Server-Side Template Injection (SSTI) vulnerability exists in the Genshi template engine due to unsafe evaluation of template expressions.

Read details

AI security incident: VU#924114: dr_flac contains an integer overflow vulnerability that allows for DoS whe...

Incident date: January 20, 2026 | Published: February 25, 2026

Overview dr_flac , an open-source FLAC audio decoder, part of the dr_libs audio decoder toolset, contains an integer overflow vulnerability allowing for denial of service (DoS) when provided a specific crafted file.

Read details

AI security incident: CVE-2026-23523 (NVD)

Incident date: January 16, 2026 | Published: February 25, 2026

Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. Prior to 0.13.

Read details

AI security incident: VU#650657: Livewire Filemanager contains an insecure .php component that allows for u...

Incident date: January 16, 2026 | Published: February 25, 2026

Overview A vulnerability, tracked as CVE-2025-14894, has been discovered within Livewire Filemanager, a tool designed for usage within Laravel applications.

Read details

AI security incident: VU#472136: Information Leak and DoS Vulnerabilities in Redmi Buds 3 Pro through 6 Pro

Incident date: January 15, 2026 | Published: February 25, 2026

Overview Redmi Buds , a series of Bluetooth earbuds produced and sold by Xiaomi , contain an Information Leak vulnerability and a Denial of Service (DoS) vulnerability in versions 3 Pro through 6 Pro.

Read details

AI security incident: CVE-2026-22813 (NVD)

Incident date: January 12, 2026 | Published: February 22, 2026

OpenCode is an open source AI coding agent. The markdown renderer used for LLM responses will insert arbitrary HTML into the DOM.

Read details

AI security incident: CVE-2025-68472 (NVD)

Incident date: January 12, 2026 | Published: February 14, 2026

MindsDB is a platform for building artificial intelligence from enterprise data. Prior to version 25.11.1, an unauthenticated path traversal in the file upload API lets any caller read arbitrary files from the server filesystem and move...

Read details

AI security incident: CVE-2026-21869 (NVD)

Incident date: January 8, 2026 | Published: February 14, 2026

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.

Read details