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
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4330 results
MEDIUMEXPLOIT AVAIL

vLLM: speculative decoding DoS via penalty params

CVE-2026-44223
6.5
EPSS 0.4%
DoSInference
vllmPatch: 0.20.0CWE-131942 ATLAS
HIGH

JupyterLab: one-click RCE via notebook HTML cell output

CVE-2026-42557
8.8
EPSS 0.5%
Code ExecutionSocial EngineeringSupply ChainFrameworkPlugin
notebookPatch: 7.5.6CWE-793.0K8 ATLAS
HIGH

OpenClaw: owner spoofing via bearer token header

CVE-2026-44118
7.8
EPSS 0.1%
Auth BypassAgentFrameworkPlugin
OpenClaw33 ATLAS
MEDIUM

OpenClaw: SSRF in QQBot media upload bypasses URL checks

CVE-2026-44117
5.8
EPSS 0.2%
Data LeakageAuth BypassAgentPluginAPI
OpenClaw32 ATLAS
HIGH

OpenClaw: SSRF in Zalo sendPhoto exposes internal resources

CVE-2026-44116
8.6
EPSS 0.3%
Data ExtractionAuth BypassAgentPlugin
OpenClaw33 ATLAS
HIGH

OpenClaw: heredoc shell expansion bypasses exec allowlist

CVE-2026-44115
8.8
EPSS 0.4%
Code ExecutionAuth BypassAgentFramework
OpenClaw34 ATLAS
HIGH

OpenClaw: dotenv namespace override enables runtime hijack

CVE-2026-44114
7.8
EPSS 0.1%
Supply ChainCode ExecutionAgentFramework
OpenClaw33 ATLAS
HIGH

OpenClaw: TOCTOU symlink race escapes sandbox mount

CVE-2026-44113
7.7
EPSS 0.2%
Data ExtractionData LeakageAgentFramework
OpenClaw34 ATLAS
CRITICAL

OpenClaw: TOCTOU symlink race escapes OpenShell sandbox

CVE-2026-44112
9.6
EPSS 7.3%
Code ExecutionSupply ChainAgentFrameworkPlugin
OpenClaw34 ATLAS1 incident
HIGHEXPLOIT AVAIL

mistune: ReDoS exposes Jupyter/AI services to DoS

CVE-2026-33079
7.5
EPSS 0.6%
DoSSupply ChainFrameworkAPI
mistunePatch: 3.2.1CWE-13331.9K4 ATLAS
LOWEXPLOIT AVAIL

Flowise: info disclosure via login API response handler

CVE-2026-8026
3.7
EPSS 0.3%
Data LeakageAuth BypassAgentFramework
flowiseCWE-2004 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: token injection DoS via multimodal placeholders

CVE-2026-44222
6.5
EPSS 0.4%
DoSPrompt InjectionInferenceModelFramework
vllmPatch: 0.20.0CWE-129945 ATLAS
HIGH

JupyterLab: Extension allow-list bypass enables privesc

CVE-2026-42266
8.8
EPSS 5.7%
Supply ChainAuth BypassCode ExecutionFrameworkPlugin
jupyterlabPatch: 4.5.7CWE-201.9K4 ATLAS
MEDIUMEXPLOIT AVAIL

wireshark-mcp: path traversal enables arbitrary file write via MCP

CVE-2026-43901
6.8
EPSS 0.3%
Prompt InjectionCode ExecutionSupply ChainAgentPlugin
CWE-225 ATLAS
HIGHEXPLOIT AVAIL

PPTAgent: eval injection enables RCE via LLM prompt injection

CVE-2026-42079
8.6
EPSS 0.1%
Prompt InjectionCode ExecutionAgentFramework
pptagentPatch: 1.1.36CWE-955 ATLAS
HIGH

openclaw: Model bypasses authz to persist unsafe config

GHSA-cwj3-vqpp-pmxr
8.8
Prompt InjectionAuth BypassCode ExecutionAgentPluginFramework
openclawPatch: 2026.4.23CWE-86235 ATLAS1 incident
HIGH

OpenClaw: RCE via malicious repo setup-api.js

GHSA-r39h-4c2p-3jxp
7.8
Supply ChainCode ExecutionAgentPlugin
openclawPatch: 2026.4.23CWE-9434 ATLAS1 incident
MEDIUM

openclaw: stale webhook secret survives credential rotation

GHSA-q8ff-7ffm-m3r9
6.0
Auth BypassAgentPlugin
openclawPatch: 2026.4.23CWE-61333 ATLAS1 incident
CRITICALEXPLOIT AVAIL

Langflow: path traversal allows arbitrary directory deletion

CVE-2026-42048
9.6
EPSS 4.2%
DoSAuth BypassFrameworkRAG
langflowPatch: 1.9.0CWE-223 ATLAS
MEDIUM

JupyterHub: CSRF bypass on spawn and share endpoints

CVE-2026-40864
5.4
EPSS 0.1%
Auth BypassDoSFramework
jupyterhubPatch: 5.4.5CWE-3521.9K4 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