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 4307 results
MEDIUM

langchain4j-aideepin: IDOR exposes other users' character chats

CVE-2026-121938
5.3
EPSS 0.4%
Data LeakageAuth BypassPrivacy ViolationFrameworkAPI
CWE-6393 ATLAS
AWAITING NVD

MLflow: unauthenticated SSRF in get-artifacts leaks data

CVE-2026-118628
--
EPSS 0.3%
Data LeakageData ExtractionFrameworkAPI
MLflowCWE-9186953 ATLAS
AWAITING NVD

MLflow: SHAP explainer deserialization allows RCE

CVE-2026-118627
--
EPSS 0.2%
Code ExecutionSupply ChainFrameworkModel
MLflowCWE-5026954 ATLAS
AWAITING NVD

MLflow: missing authorization allows privilege escalation

CVE-2026-118626
--
EPSS 0.2%
Auth BypassData LeakageFrameworkTraining Data
MLflowCWE-8626953 ATLAS
AWAITING NVD

MLflow: missing authorization allows privilege escalation

CVE-2026-118625
--
EPSS 0.3%
Auth BypassData LeakageFrameworkAPI
MLflowCWE-8626953 ATLAS
AWAITING NVD

MLflow: missing authz in jobs allows info disclosure

CVE-2026-118624
--
EPSS 0.4%
Data LeakageAuth BypassFrameworkTraining Data
MLflowCWE-8626953 ATLAS
AWAITING NVD

MLflow: pickle deserialization enables RCE

CVE-2026-118623
--
EPSS 0.4%
Code ExecutionSupply ChainFrameworkModelTraining Data
MLflowCWE-5026954 ATLAS
HIGH

Stanza: unsafe pickle in lemma model load enables RCE

CVE-2026-115878
7.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkModel
stanzaPatch: 1.15.0CWE-9426.1K5 ATLAS
HIGH

Claude Code: TOCTOU symlink race lets sandbox escape file write

CVE-2026-88968
--
EPSS 0.3%
Code ExecutionSupply ChainAgentPlugin
claude-code4 ATLAS
AWAITING NVD

Claude Desktop: untrusted search path runs rogue git.exe

CVE-2026-88066
--
EPSS 0.3%
Code ExecutionSupply ChainAgentPlugin
claude-codeCWE-4273 ATLAS
MEDIUM

APM Server: OTLP memory exhaustion causes DoS

CVE-2026-115716
6.5
EPSS 0.4%
DoSAPIFramework
2 ATLAS
HIGH

Elastic Docker images: compromised eMudhra CAs enable TLS MITM

CVE-2026-115714
7.4
EPSS 0.2%
Supply ChainData LeakageFramework
1 ATLAS
MEDIUM

Elastic APM Server: config mixup leaks other services' settings

CVE-2026-115289
4.3
EPSS 0.2%
Data LeakageAuth BypassFrameworkAPI
2 ATLAS
MEDIUM

FreeRDP proxy: DVC reassembly memory exhaustion DoS

CVE-2026-121412
6.5
EPSS 0.4%
DoSFramework
CWE-7701 ATLAS
HIGH

Label Studio: SSRF in export leaks internal data, API token

CVE-2026-121561
7.7
EPSS 0.4%
Data ExtractionAuth BypassData LeakageFrameworkTraining Data
label-studio25 ATLAS
AWAITING NVD

Android SystemUI: URI squatting enables spoofed Quick Controls

CVE-2026-58930
--
EPSS 0.1%
Auth BypassSocial EngineeringFramework
MEDIUM

DBHub: read-only bypass via MySQL comment parsing

GHSA-j656-3hf2-fvjc
--
Auth BypassPrompt InjectionAgentPluginFramework
CWE-4364 ATLAS
AWAITING NVD

CrewAI: SSRF guard parser differential enables internal access

CVE-2026-120630
--
EPSS 0.2%
Data LeakagePrompt InjectionAuth BypassAgentFrameworkPlugin
CrewAI3714 ATLAS
MEDIUM

Chainlit: SSRF via semicolon bypass of MCP allowed_urls

CVE-2026-120492
5.4
EPSS 0.2%
Auth BypassData LeakageFrameworkPluginAgent
chainlitCWE-918412 ATLAS
AWAITING NVD

Apache Wicket: JS escaping flaw enables XSS

CVE-2026-83559
--
EPSS 0.3%
Code ExecutionData LeakageFramework
CWE-1161 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