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
SeverityCVE IDSummaryCVSSEPSSPackageDate
MEDICVE-2026-121938langchain4j-aideepin: IDOR exposes other users' character chats5.30.4%—Nov 4UNKNCVE-2026-118628MLflow: unauthenticated SSRF in get-artifacts leaks data—0.3%MLflowNov 3UNKNCVE-2026-118627MLflow: SHAP explainer deserialization allows RCE—0.2%MLflowNov 3UNKNCVE-2026-118626MLflow: missing authorization allows privilege escalation—0.2%MLflowNov 3UNKNCVE-2026-118625MLflow: missing authorization allows privilege escalation—0.3%MLflowNov 3UNKNCVE-2026-118624MLflow: missing authz in jobs allows info disclosure—0.4%MLflowNov 3UNKNCVE-2026-118623MLflow: pickle deserialization enables RCE—0.4%MLflowNov 3HIGHCVE-2026-88968Claude Code: TOCTOU symlink race lets sandbox escape file write—0.3%claude-codeNov 3UNKNCVE-2026-88066Claude Desktop: untrusted search path runs rogue git.exe—0.3%claude-codeNov 3MEDICVE-2026-115716APM Server: OTLP memory exhaustion causes DoS6.50.4%—Nov 3HIGHCVE-2026-115714Elastic Docker images: compromised eMudhra CAs enable TLS MITM7.40.2%—Nov 3MEDICVE-2026-115289Elastic APM Server: config mixup leaks other services' settings4.30.2%—Nov 3MEDICVE-2026-121412FreeRDP proxy: DVC reassembly memory exhaustion DoS6.50.4%—Nov 3HIGHCVE-2026-121561Label Studio: SSRF in export leaks internal data, API token7.70.4%label-studioNov 3UNKNCVE-2026-58930Android SystemUI: URI squatting enables spoofed Quick Controls—0.1%—Nov 2MEDIGHSA-j656-3hf2-fvjcDBHub: read-only bypass via MySQL comment parsing———Nov 2UNKNCVE-2026-120630CrewAI: SSRF guard parser differential enables internal access—0.2%CrewAINov 2MEDICVE-2026-120492Chainlit: SSRF via semicolon bypass of MCP allowed_urls5.40.2%chainlitNov 2UNKNCVE-2026-83559Apache Wicket: JS escaping flaw enables XSS—0.3%—Nov 1LOWCVE-2026-82898Wicket: resource isolation bypass replays forged forms—0.3%—Nov 1

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