ASR AI Security Radar
Back to homepage

Recent AI Security Incidents

This archive includes all published incident pages. Page 10 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: Kata Container to Guest micro VM privilege escalation (GHSA-wwj6-vghv-5p64)

Incident date: February 19, 2026 | Published: February 25, 2026

Summary An issue in Kata with Cloud Hypervisor allows a user of the container to modify the file system used by the Guest micro VM ultimately achieving arbitrary code execution as root in said VM.

Read details

AI security incident: Unauthorized npm publish of cline@2.3.0 with modified postinstall script (GHSA-9ppg-j...

Incident date: February 19, 2026 | Published: February 25, 2026

Description On February 17, 2026 at 3:26 AM PT, an unauthorized party used a compromised npm publish token to publish an update to Cline CLI on the NPM registry: cline@2.3.0. The published package contains a modified package.

Read details

AI security incident: Kargo has an Authorization Bypass Vulnerability in Batch Resource Creation API Endpoi...

Incident date: February 19, 2026 | Published: February 25, 2026

Summary The batch resource creation endpoints of both Kargo's legacy gRPC API and newer REST API accept multi-document YAML payloads.

Read details

AI security incident: Kargo has Missing Authorization Vulnerabilities in Approval & Promotion REST API Endp...

Incident date: February 19, 2026 | Published: February 25, 2026

Summary Kargo's authorization model includes a promote verb -- a non-standard Kubernetes ["dolphin verb"](https://www.aquasec.com/blog/kubernetes-verbs/) -- that gates the ability to advance Freight through a promotion pipeline.

Read details

AI security incident: Fabric.js Affected by Stored XSS via SVG Export (GHSA-hfvx-25r5-qc3w)

Incident date: February 18, 2026 | Published: February 25, 2026

fabric.js applies escapeXml() to text content during SVG export ( src/shapes/Text/TextSVGExportMixin.ts:186 ) but fails to apply it to other user-controlled string values that are interpolated into SVG attribute markup.

Read details

AI security incident: OpenClaw session tool visibility hardening and Telegram webhook secret fallback (GHSA...

Incident date: February 18, 2026 | Published: February 25, 2026

Vulnerability In some shared-agent deployments, OpenClaw session tools ( sessions_list , sessions_history , sessions_send ) allowed broader session targeting than some operators intended.

Read details

AI security incident: OpenClaw: Docker container escape via unvalidated bind mount config injection (GHSA-w...

Incident date: February 18, 2026 | Published: February 25, 2026

Summary A configuration injection issue in the Docker tool sandbox could allow dangerous Docker options (bind mounts, host networking, unconfined profiles) to be applied, enabling container escape or host data access.

Read details

AI security incident: Keras has a Local File Disclosure via HDF5 External Storage During Keras Weight Loadi...

Incident date: February 18, 2026 | Published: February 25, 2026

Summary TensorFlow / Keras continues to honor HDF5 “external storage” and ExternalLink features when loading weights. A malicious .weights.h5 (or a .

Read details

AI security incident: RediSearch Query Injection in @langchain/langgraph-checkpoint-redis (GHSA-5mx2-w598-3...

Incident date: February 18, 2026 | Published: February 25, 2026

Summary A query injection vulnerability exists in the @langchain/langgraph-checkpoint-redis package's filter handling.

Read details

AI security incident: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern (GH...

Incident date: February 18, 2026 | Published: February 25, 2026

Summary minimatch is vulnerable to Regular Expression Denial of Service (ReDoS) when a glob pattern contains many consecutive * wildcards followed by a literal character that doesn't appear in the test string.

Read details