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
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1527 results — Medium severity
MEDIUM

n8n: prototype pollution DoS via Edit Fields node

CVE-2026-72749
6.5
EPSS 0.6%
DoSAgentFramework
n8nCWE-132116
MEDIUM

Craft CMS: read-only role can restructure categories

CVE-2026-72785
4.3
EPSS 0.3%
Auth BypassPlugin
MEDIUMEXPLOIT AVAIL

Ray Enterprise Translation WP plugin: broken access control

CVE-2026-14549
4.3
EPSS 0.3%
Auth BypassPlugin
Ray Enterprise Translation642
MEDIUMEXPLOIT AVAIL

Ray Translation WP: Subscribers can hijack API token

CVE-2026-14548
6.5
EPSS 0.3%
Auth BypassPluginAPI
Ray Enterprise Translation642
MEDIUM

Feast operator: code injection escalates to cluster admin

CVE-2026-18942
5.5
EPSS 0.4%
Code ExecutionSupply ChainData LeakageFrameworkTraining Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel93.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

Keras: OOM DoS via malicious .keras model load

CVE-2026-12570
5.5
EPSS 0.2%
DoSSupply ChainFrameworkModel
kerasPatch: 3.15.0CWE-7704.1K4 ATLAS
MEDIUM

Ollama-mcp: command injection via model args

CVE-2026-19334
5.3
EPSS 1.1%
Code ExecutionAgentPlugin
CWE-742 ATLAS
MEDIUM

JupyterHub: unauth log flooding via long usernames

CVE-2026-54338
5.3
EPSS 0.4%
DoSFramework
jupyterhubPatch: 5.5.0CWE-4001.9K1 ATLAS
MEDIUM

NLTK: downloader cross-package poisoning of models

CVE-2026-12261
5.3
EPSS 0.2%
Supply ChainModel PoisoningFrameworkTraining Data
CWE-2844 ATLAS
MEDIUM

Craft CMS: view-only role can restructure categories

GHSA-xxpx-f366-4xpq
--
Auth BypassPlugin
craftcms/cmsPatch: 5.10.6CWE-863514
MEDIUM

LangGraph Checkpoint: prefix match leaks cross-tenant data

CVE-2026-71433
5.3
EPSS 0.4%
Data LeakageAuth BypassFrameworkAgent
langgraph-checkpoint-sqlitePatch: 3.1.1CWE-2004.1K2 ATLAS
MEDIUM

Non-AI false positive: WordPress theme, not ML Accelerate

CVE-2025-9266
4.3
EPSS 0.3%
Auth BypassPlugin
AccelerateCWE-8623.1K
MEDIUMEXPLOIT AVAIL

openclaw-cn: symlink escape bypasses agent sandbox

CVE-2026-19008
6.3
EPSS 0.4%
Code ExecutionAuth BypassAgentPlugin
CWE-593 ATLAS
MEDIUMEXPLOIT AVAIL

openclaw-cn: broken privilege check on elevated senders

CVE-2026-19007
6.3
EPSS 0.4%
Auth BypassAgent
CWE-2662 ATLAS
MEDIUMEXPLOIT AVAIL

openclaw-cn: auth bypass in bash exec approval gate

CVE-2026-19006
6.3
EPSS 0.4%
Auth BypassCode ExecutionAgent
CWE-2852 ATLAS
MEDIUM

Livebook: CSRF binds victim session to attacker

CVE-2026-66885
6.5
EPSS 0.2%
Auth BypassSocial EngineeringFramework
2 ATLAS
MEDIUMEXPLOIT AVAIL

InnoShop: path traversal in file manager deletes files

CVE-2026-18959
5.4
EPSS 0.5%
DoSFramework
1 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file write

CVE-2026-7869
5.4
EPSS 0.3%
Code ExecutionSupply ChainFrameworkRAG
langflowCWE-222 ATLAS
MEDIUM

Langflow: username path traversal enables data destruction

CVE-2026-7658
6.5
EPSS 0.5%
Auth BypassDoSFrameworkAgent
langflowCWE-221 ATLAS
MEDIUM

Langflow: built-in component leaks server env vars

CVE-2026-10128
6.5
EPSS 0.3%
Data LeakagePrivacy ViolationFrameworkPlugin
langflowCWE-2003 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