AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
3,019

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 400 results — Medium severity, has patch
MEDIUM

Craft CMS:Authorization bypass: view-only Categories user can modify category structure via structures/move-element

GHSA-xxpx-f366-4xpq
--
craftcms/cms Patch: 5.10.6 CWE-863 492
MEDIUM

LangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite stores

CVE-2026-71433
5.3
EPSS 0.2%
langgraph-checkpoint-sqlite Patch: 3.1.1 CWE-200 3.7K
MEDIUM

Ghost: Blind Password Hash Disclosure in Ghost Admin API

CVE-2026-70590
4.8
EPSS 0.2%
ghost Patch: 6.54.1 CWE-200
MEDIUM

Open WebUI: Any authenticated user can stall a worker via a knowledge-search pattern that backtracks catastrophically

CVE-2026-70493
6.5
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-1333 4
MEDIUM

Open WebUI: Tool source code disclosed to read-only users via the tool list and get endpoints

CVE-2026-70491
6.5
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-200 4
MEDIUM

Open WebUI: Unapproved accounts can open terminal sessions via a WebSocket auth path missing the role check

CVE-2026-70490
6.3
EPSS 0.2%
open-webui Patch: 0.11.0 CWE-863 4
MEDIUM

Open WebUI: Instance-wide stall via automation recurrence rules that force multi-second parsing

CVE-2026-70489
6.5
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-400 4
MEDIUM

Open WebUI: DNS Rebinding SSRF Bypass

CVE-2026-54020
6.3
EPSS 0.2%
open-webui Patch: 0.11.0 CWE-367 4
MEDIUM

Open WebUI: Cross-user file content disclosure via request-scoped direct model knowledge metadata

CVE-2026-70487
5.3
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-862 4
MEDIUM

Open WebUI: Deletion of directories and file embeddings in other knowledge bases via sync cleanup

CVE-2026-70488
4.3
EPSS 0.2%
open-webui Patch: 0.11.0 CWE-639 4
MEDIUM

Open WebUI: Users denied the image-generation permission can still generate images via chat completions

CVE-2026-70484
4.3
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-862 4
MEDIUM

Open WebUI: Client-side SSRF via unrestricted external resource loading in Vega/Vega-Lite chart rendering

CVE-2026-70480
4.1
EPSS 0.2%
open-webui Patch: 0.11.0 CWE-918 4
MEDIUM

Open WebUI: Any member with write access to a standard channel can edit or delete other members' messages

CVE-2026-70481
5.4
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-284 4
MEDIUM

Flowise: Unauthenticated Credential Abuse via Text-to-Speech Endpoint Allows Unauthorized Use of Private Chatflow TTS Credentials

GHSA-8gj2-2cvc-6xx7
--
flowise Patch: 3.1.4 CWE-862
MEDIUM

Flowise: Incomplete Credential Redaction Exposes Secrets via API

GHSA-rwrp-9823-p2xq
6.5
flowise Patch: 3.1.3 CWE-200
MEDIUM

Flowise: IDOR vulnerability exists at the GET /api/v1/organization/customer-default-source endpoint

GHSA-2364-jh4q-m9vm
--
flowise Patch: 3.1.3 CWE-639
MEDIUM

A vulnerability in keras-team/keras versions <= 3.14.0 allows arbitrary local HDF5 file content disclosure due to improper handling of HDF5 ExternalLinks. The...

CVE-2026-9335
6.5
EPSS 0.6%
keras Patch: 3.12.3 CWE-22 1.5K
MEDIUM

n8n: SQL injection in Snowflake Execute Query node

GHSA-652q-gvq3-74qv
--
Code Execution Data Leakage Agent Framework
n8n Patch: 1.123.67 CWE-89 16 3 ATLAS
MEDIUM

n8n: SQL injection in Postgres Trigger node

GHSA-jqwr-vx3p-r266
--
Code Execution Data Leakage Agent Plugin
n8n Patch: 1.123.67 CWE-89 16 3 ATLAS
MEDIUM

n8n: shared module cache poisoning breaks user isolation

GHSA-9cmh-xcqm-5hqr
--
Code Execution Privacy Violation Agent Plugin
n8n Patch: 1.123.67 CWE-20 16 1 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial