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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 2876 results — no patch
HIGH

MONAI: pickle cache deserialization allows local code execution

CVE-2026-100841
7.8
EPSS 0.1%
Code ExecutionSupply ChainFrameworkTraining Data
monaiCWE-5021284 ATLAS
HIGHEXPLOIT AVAIL

MONAI: code execution via malicious bundle config

CVE-2026-100840
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkModel
monaiCWE-951285 ATLAS
HIGH

Froxlor: TOCTOU symlink race in SSH key cron gives root

CVE-2026-100713
7.8
EPSS 0.2%
Code ExecutionAuth BypassFramework
CWE-3672 ATLAS
MEDIUMEXPLOIT AVAIL

Froxlor: CSRF on GET silently disables 2FA

CVE-2026-100712
6.5
EPSS 0.1%
Auth BypassSocial EngineeringFramework
CWE-3522 ATLAS
HIGHEXPLOIT AVAIL

Froxlor: sessions and API keys survive password change

CVE-2026-100711
7.5
EPSS 0.3%
Auth BypassFramework
CWE-6132 ATLAS
MEDIUM

vLLM: out-of-range stop_token_ids crash EngineCore (DoS)

CVE-2026-100654
6.5
EPSS 0.3%
DoSInferenceAPI
vllmCWE-129943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: revision pin bypass loads unpinned HF artifacts

CVE-2026-100653
6.5
EPSS 0.3%
Supply ChainInferenceFrameworkModel
vllmCWE-348943 ATLAS
HIGH

vLLM: invalid stop_token_ids crash EngineCore (DoS)

CVE-2026-100652
7.5
EPSS 0.4%
DoSInferenceAPI
vllmCWE-20943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: prompt-length bypass on disagg endpoint causes DoS

CVE-2026-100651
6.5
EPSS 0.4%
DoSInferenceAPI
vllmCWE-400943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: unbounded media fetch enables pre-inference DoS

CVE-2026-100650
6.5
EPSS 0.8%
DoSInferenceAPI
vllmCWE-400943 ATLAS
MEDIUM

vLLM: sampler subclass bypass exhausts GPU memory

CVE-2026-100649
5.3
EPSS 0.3%
DoSInferenceFramework
vllmCWE-770944 ATLAS
MEDIUM

vLLM: audio size limit bypass enables resource exhaustion

CVE-2026-100648
5.3
EPSS 0.4%
DoSInferenceAPI
vllmCWE-400943 ATLAS
HIGH

vLLM: unbounded cache_salt allows unauthenticated DoS

CVE-2026-100647
7.5
EPSS 0.3%
DoSInferenceAPI
vllmCWE-20943 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: SQL injection leaks all notebook data

CVE-2026-100644
7.5
EPSS 0.4%
Data ExtractionData LeakageFrameworkAPI
CWE-892 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: path traversal in setNotebookIcon writes files

CVE-2026-100638
7.6
EPSS 0.6%
Code ExecutionFramework
CWE-732 ATLAS
MEDIUM

SiYuan: MCP file guard bypass exposes protected files

CVE-2026-100633
6.5
EPSS 0.4%
Data ExtractionAuth BypassData LeakageAgentPluginFramework
CWE-8635 ATLAS
HIGHEXPLOIT AVAIL

Flowise: missing authz in upsert-history exposes configs

CVE-2026-100610
7.5
EPSS 0.3%
Auth BypassData LeakageData ExtractionFrameworkRAGAgent
flowiseCWE-6395 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: cross-workspace credential IDOR exposes API keys

CVE-2026-100609
6.8
EPSS 0.3%
Auth BypassData LeakageFrameworkAgentAPI
CWE-6394 ATLAS
HIGHEXPLOIT AVAIL

Flowise: BullMQ dashboard authz gap exposes all tenants

CVE-2026-100608
8.3
EPSS 0.3%
Auth BypassData LeakageData ExtractionFrameworkAgentAPI
flowiseCWE-8624 ATLAS
HIGHEXPLOIT AVAIL

Flowise: SSO email-only matching enables account takeover

CVE-2026-100607
7.7
EPSS 0.4%
Auth BypassData LeakageFrameworkAgent
flowiseCWE-2874 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