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 544 results — Medium severity, has patch
MEDIUMEXPLOIT AVAIL

Pillow: TIFF tile heap over-read enables DoS and memory leak

CVE-2026-112395
6.5
EPSS 0.5%
DoSData LeakageFrameworkInference
pillowPatch: 13.0.0CWE-1226.3K3 ATLAS
MEDIUM

Mercury: stored XSS via unsanitized Markdown HTML

CVE-2026-111059
6.1
EPSS 0.3%
Code ExecutionData LeakageFramework
mercuryPatch: 3.2.11CWE-793.0K2 ATLAS
MEDIUM

JupyterLab: trust prompt race marks wrong document trusted

CVE-2026-102832
4.2
EPSS 0.1%
Auth BypassCode ExecutionFramework
jupyterlite-corePatch: 0.8.4CWE-3671.9K2 ATLAS
MEDIUM

Coraza WAF: Content-Type parsing flaw bypasses body inspection

GHSA-w253-m66g-rx24
5.8
Auth BypassAPIFramework
github.com/corazawaf/coraza/v3Patch: 3.8.1CWE-206.3K3 ATLAS
MEDIUM

Coraza WAF: filename* charset bypass evades upload rules

GHSA-3wr7-993q-jrff
4.0
Auth BypassAPIFramework
github.com/corazawaf/coraza/v3Patch: 3.8.1CWE-206.3K2 ATLAS
MEDIUM

Coraza WAF: cookie parser mismatch enables WAF bypass

GHSA-g4qm-m288-5cp9
4.0
Auth BypassAPIFramework
github.com/corazawaf/coraza/v3Patch: 3.8.1CWE-4366.3K2 ATLAS
MEDIUM

Coraza WAF: malformed URI bypasses GET arg inspection

GHSA-x26q-wvhg-fh4m
4.0
Auth BypassAPIFramework
github.com/corazawaf/coraza/v3Patch: 3.8.0CWE-206.3K2 ATLAS
MEDIUMEXPLOIT AVAIL

Coraza WAF: octal jsDecode bug lets payloads bypass rules

CVE-2026-104774
5.8
EPSS 0.3%
Auth BypassFrameworkAPI
github.com/corazawaf/coraza/v3Patch: 3.8.0CWE-1726.3K3 ATLAS
MEDIUM

Coraza WAF: JSON key collision bypasses inspection

GHSA-5gj4-9gm7-2fx2
5.8
Auth BypassAPIFramework
github.com/corazawaf/coraza/v3Patch: 3.8.1CWE-206.3K2 ATLAS
MEDIUM

RabbitMQ Java Client: AMQP password leaked in exception

CVE-2026-106123
--
EPSS 0.2%
Data LeakagePrivacy ViolationFrameworkAPI
com.rabbitmq:amqp-clientPatch: 5.35.0CWE-5092 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI Platform: authz flaw lets members delete issue links

CVE-2026-62179
6.5
EPSS 0.2%
Auth BypassAgentFrameworkAPI
praisonai-platformPatch: 0.1.9CWE-86212 ATLAS
MEDIUM

LangChain MongoDB: NoSQL injection exposes chat histories

CVE-2026-106119
--
EPSS 0.5%
Data LeakageAuth BypassFrameworkAPI
@langchain/mongodbPatch: 1.3.1CWE-9433.2K4 ATLAS
MEDIUM

Langflow: SSRF in built-in components exposes cloud metadata

GHSA-j8f7-x8jm-wmm4
--
Data LeakageData ExtractionFrameworkAgentPlugin
lfx-doclingPatch: 0.1.2CWE-9184 ATLAS
MEDIUM

vLLM: unbounded video frame decoding enables DoS

CVE-2026-105758
5.3
EPSS 0.3%
DoSInferenceAPI
vllmPatch: 0.30.0CWE-770943 ATLAS
MEDIUM

vLLM: unbounded video frame options enable DoS

CVE-2026-105760
5.3
EPSS 0.3%
DoSInferenceAPI
vllmPatch: 0.30.0CWE-400943 ATLAS
MEDIUM

vLLM: input validation flaws let attacker crash EngineCore

CVE-2026-105754
6.5
EPSS 0.3%
DoSData LeakageAuth BypassInferenceAPIModel
vllmPatch: 0.30.0CWE-20944 ATLAS
MEDIUM

vLLM: unhandled structured-output errors crash engine (DoS)

CVE-2026-105757
6.5
EPSS 0.3%
DoSInferenceFrameworkAPI
vllmPatch: 0.30.0CWE-20943 ATLAS
MEDIUM

vLLM: request-ID cache key collision corrupts rerank scores

CVE-2026-105755
4.2
EPSS 0.2%
Auth BypassDoSInferenceAPIRAG
vllmPatch: 0.30.0CWE-639944 ATLAS
MEDIUM

vLLM: unvalidated cache_salt crashes EngineCore (DoS)

CVE-2026-105756
6.5
EPSS 0.3%
DoSInferenceAPI
vllmPatch: 0.30.0CWE-20942 ATLAS
MEDIUM

vLLM: reachable assertion in cache causes DoS

CVE-2026-105753
6.5
EPSS 0.4%
DoSInferenceFramework
vllmPatch: 0.28.0CWE-617943 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