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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4331 results
UNKNOWN

n8n: Python sandbox escape enables container RCE

CVE-2026-49444
--
EPSS 0.4%
Code ExecutionData ExtractionAgentFrameworkPlugin
n8nPatch: 1.123.48CWE-20165 ATLAS
CRITICALEXPLOIT AVAIL

vllm: auth bypass exposes OpenAI inference API

CVE-2026-48746
9.1
EPSS 1.2%
Auth BypassDoSData ExtractionInferenceAPI
vllmPatch: 0.22.0CWE-444946 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: unauth file read via Shareable Playground

CVE-2026-48520
6.1
EPSS 0.4%
Data ExtractionData LeakageAuth BypassFrameworkAgent
langflowPatch: 1.10.0CWE-735 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: unauthenticated RCE via Shareable Playground

CVE-2026-48519
9.6
EPSS 0.8%
Code ExecutionAuth BypassFrameworkAgent
langflowPatch: 1.9.2CWE-945 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: path traversal enables arbitrary file write

CVE-2026-42867
6.5
EPSS 0.5%
Code ExecutionData LeakageSupply ChainFrameworkRAG
langflowPatch: 1.9.0CWE-223 ATLAS
HIGH

vLLM: assert bypass → RCE via poisoned HuggingFace model

CVE-2026-41523
7.5
EPSS 0.9%
Supply ChainCode ExecutionInferenceModel
vllmPatch: 0.22.0CWE-94945 ATLAS
HIGHEXPLOIT AVAIL

Langflow: IDOR exposes cross-user LLM data and deletion

CVE-2026-33760
8.8
EPSS 0.5%
Auth BypassData ExtractionPrivacy ViolationFrameworkAgent
langflowPatch: 1.9.0CWE-6394 ATLAS
MEDIUM

LangChain: path traversal exposes files outside sandbox

GHSA-gr75-jv2w-4656
5.1
Data ExtractionAuth BypassFrameworkAgent
langchain-anthropicPatch: 1.4.6CWE-223.2K4 ATLAS
HIGHEXPLOIT AVAIL

NLTK: path traversal leaks arbitrary local files

CVE-2026-54293
7.5
EPSS 0.6%
Data ExtractionPrivacy ViolationFramework
nltkPatch: 3.10.0CWE-223.0K5 ATLAS
MEDIUM

Nuxt: local unauth IPC leaks .env secrets on shared hosts

GHSA-534h-c3cw-v3h9
5.5
Data ExtractionData LeakageFrameworkAPI
nuxtPatch: 4.4.7CWE-2766.3K4 ATLAS
HIGH

Nuxt: auth bypass via URL case-sensitivity mismatch

CVE-2026-53721
--
EPSS 0.4%
Auth BypassFrameworkAPI
nuxtPatch: 4.4.7CWE-1786.3K3 ATLAS
MEDIUM

Nuxt: open redirect + XSS in navigation API (SSR+client)

GHSA-c9cv-mq2m-ppp3
6.1
EPSS 0.4%
Auth BypassSocial EngineeringCode ExecutionFrameworkAPI
nuxtPatch: 4.4.7CWE-796.3K5 ATLAS
MEDIUM

OpenClaw: hostname prefix bypass leaks auth tokens

CVE-2026-53839
6.5
EPSS 0.3%
Auth BypassData ExtractionAgentFramework
OpenClawCWE-102333 ATLAS1 incident
CRITICAL

OpenClaw: approval scope bypass via reconnection state

CVE-2026-53838
9.8
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
OpenClawCWE-36734 ATLAS1 incident
LOW

OpenClaw: DM policy bypass via Mattermost event spoofing

CVE-2026-53837
3.7
EPSS 0.2%
Auth BypassAgentPlugin
OpenClawCWE-63633 ATLAS1 incident
HIGH

OpenClaw: PowerShell allowlist bypass enables arbitrary RCE

CVE-2026-53836
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgent
OpenClawCWE-18434 ATLAS1 incident
MEDIUM

OpenClaw: auth bypass in Feishu agent binding controls

CVE-2026-53835
4.3
EPSS 0.2%
Auth BypassAgent
OpenClawCWE-86334 ATLAS1 incident
HIGH

OpenClaw: auth bypass in QQBot pre-dispatch commands

CVE-2026-53834
7.5
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
OpenClawCWE-86333 ATLAS1 incident
HIGH

OpenClaw: auth bypass allows agent config mutation

CVE-2026-53833
7.7
EPSS 0.2%
Auth BypassData LeakageAgentFramework
openclawCWE-29033 ATLAS
HIGH

OpenClaw: identity header spoof grants operator access

CVE-2026-53832
7.7
EPSS 0.1%
Auth BypassCode ExecutionAgentFramework
OpenClawCWE-29035 ATLAS1 incident

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