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

open-webui: mass assignment enables cross-user folder injection

CVE-2026-44550
5.0
EPSS 0.3%
Auth BypassSocial EngineeringPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.9.0CWE-86224 ATLAS
MEDIUMEXPLOIT AVAIL

BentoML: symlink traversal exfiltrates host secrets at build

CVE-2026-40610
5.5
EPSS 0.3%
Data ExtractionSupply ChainFramework
bentomlPatch: 1.4.39CWE-59234 ATLAS
MEDIUM

@axonflow/openclaw: credential exposure via insecure file permissions

GHSA-cqmh-pcgr-q42f
5.5
Data LeakageAuth BypassPrivacy ViolationPluginAgent
@axonflow/openclawPatch: 2.0.0CWE-55235 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: speculative decoding DoS via penalty params

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

OpenClaw: SSRF in QQBot media upload bypasses URL checks

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

openclaw: stale webhook secret survives credential rotation

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

LobeChat: XSS-to-RCE via exposed Electron IPC

CVE-2026-42045
6.2
EPSS 0.3%
Code ExecutionPrompt InjectionSocial EngineeringAPIAgent
@lobehub/lobehubCWE-781.8K6 ATLAS
MEDIUMEXPLOIT AVAIL

jupyter-server: auth cookie survives password reset

CVE-2026-40934
6.8
EPSS 0.3%
Auth BypassData ExtractionFrameworkAPI
jupyter-serverPatch: 2.18.0CWE-6131.9K4 ATLAS
MEDIUMEXPLOIT AVAIL

jupyter-server: Open redirect enables credential phishing

CVE-2025-61669
--
EPSS 0.2%
Social EngineeringAuth BypassFrameworkAPI
jupyter-serverPatch: 2.18.0CWE-6011.9K5 ATLAS
MEDIUMEXPLOIT AVAIL

Langchain-Chatchat: auth bypass on file service endpoints

CVE-2026-7844
6.3
EPSS 0.3%
Auth BypassData ExtractionFrameworkRAG
CWE-2875 ATLAS
MEDIUM

OpenClaw: symlink traversal exposes host filesystem

CVE-2026-43570
6.5
EPSS 0.3%
Supply ChainData ExtractionAgentPlugin
openclawPatch: 2026.4.5CWE-6134 ATLAS1 incident
MEDIUM

openclaw: auth bypass exposes Gateway bootstrap config

GHSA-93rg-2xm5-2p9v
--
Auth BypassData LeakageAgentAPI
openclawPatch: 2026.4.22CWE-28734 ATLAS1 incident
MEDIUM

openclaw: TOCTOU race allows out-of-sandbox file read

GHSA-5h3g-6xhh-rg6p
--
Data ExtractionPrivacy ViolationAgentPlugin
openclawPatch: 2026.4.22CWE-36734 ATLAS1 incident
MEDIUM

OpenClaw: exec allowlist bypass allows hidden shell code

GHSA-x3h8-jrgh-p8jx
--
Code ExecutionAuth BypassAgentPlugin
openclawPatch: 2026.4.22CWE-20034 ATLAS1 incident
MEDIUM

OpenClaw: .env injection redirects connector endpoints

GHSA-55cf-xx38-4p9p
--
Supply ChainAuth BypassData ExtractionAgentPlugin
openclawPatch: 2026.4.22CWE-42734 ATLAS1 incident
MEDIUM

openclaw: ACP child session security envelope bypass

GHSA-q3jj-46pq-826r
--
Auth BypassCode ExecutionAgentFramework
openclawPatch: 2026.4.22CWE-27734 ATLAS1 incident
MEDIUM

openclaw: SSRF bypass via Zalo plugin photo URLs

GHSA-2hh7-c75g-qj2r
--
Auth BypassData ExtractionAgentPlugin
openclawPatch: 2026.4.22CWE-91833 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