ASR AI Security Radar
Back to homepage

Recent AI Security Incidents

This archive includes all published incident pages. Page 2 of 16.

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: WeKnora Vulnerable to Remote Code Execution via SQL Injection Bypass in AI Database Q...

Incident date: March 6, 2026 | Published: March 7, 2026

WeKnora Vulnerable to Remote Code Execution via SQL Injection Bypass in AI Database Query Tool Summary A critical Remote Code Execution (RCE) vulnerability exists in the application's database query functionality.

Read details

AI security incident: Zarf's symlink targets in archives are not validated against destination directory (G...

Incident date: March 6, 2026 | Published: March 6, 2026

Zarf's symlink targets in archives are not validated against destination directory Summary A path traversal vulnerability in archive extraction allows a specifically crafted Zarf package to create symlinks pointing outside the destination...

Read details

AI security incident: Mercurius's queryDepth limit bypassed for WebSocket subscriptions (GHSA-m4h2-mjfm-mp55)

Incident date: March 6, 2026 | Published: March 6, 2026

Mercurius's queryDepth limit bypassed for WebSocket subscriptions Description Mercurius fails to enforce the configured queryDepth limit on GraphQL subscription queries received over WebSocket connections.

Read details

AI security incident: parse-server's endpoint /loginAs allows readOnlyMasterKey to gain full read and write...

Incident date: March 6, 2026 | Published: March 6, 2026

parse-server's endpoint /loginAs allows readOnlyMasterKey to gain full read and write access as any user Impact The readOnlyMasterKey can call POST /loginAs to obtain a valid session token for any user.

Read details

AI security incident: GitHub Copilot CLI Dangerous Shell Expansion Patterns Enable Arbitrary Code Execution...

Incident date: March 6, 2026 | Published: March 6, 2026

GitHub Copilot CLI Dangerous Shell Expansion Patterns Enable Arbitrary Code Execution Summary A security vulnerability has been identified in GitHub Copilot CLI's shell tool that could allow arbitrary code execution through crafted bash...

Read details

AI security incident: Pingora vulnerable to HTTP Request Smuggling via Premature Upgrade (GHSA-xq2h-p299-vjwv)

Incident date: March 5, 2026 | Published: March 5, 2026

Pingora vulnerable to HTTP Request Smuggling via Premature Upgrade Impact Pingora versions prior to 0.8.0 would immediately forward bytes following a request with an Upgrade header to the backend, without waiting for a 101 Switching...

Read details

AI security incident: Gogs: Release tag option injection in release deletion (GHSA-v9vm-r24h-6rqm)

Incident date: March 5, 2026 | Published: March 5, 2026

Gogs: Release tag option injection in release deletion Summary There is a security issue in Gogs where deleting a release can fail if a user-controlled tag name is passed to Git without the right separator, allowing Git...

Read details

AI security incident: Gogs: Cross-repository LFS object overwrite via missing content hash verification (GH...

Incident date: March 5, 2026 | Published: March 5, 2026

Gogs: Cross-repository LFS object overwrite via missing content hash verification Summary Overwritable LFS object across different repos leads to supply-chain attack, all LFS objects are vulnerable to be maliciously overwritten by...

Read details

AI security incident: SVGO DoS through entity expansion in DOCTYPE (Billion Laughs) (GHSA-xpqw-6gx7-v673)

Incident date: March 4, 2026 | Published: March 4, 2026

SVGO DoS through entity expansion in DOCTYPE (Billion Laughs) Summary SVGO accepts XML with custom entities, without guards against entity expansion or recursion.

Read details

AI security incident: Fickling missing RCE-capable modules in UNSAFE IMPORTS (GHSA-5hwf-rc88-82xm)

Incident date: March 4, 2026 | Published: March 4, 2026

Fickling missing RCE-capable modules in UNSAFE IMPORTS Assessment The modules uuid, osx support and aix support were added to the blocklist of unsafe imports (https://github.

Read details