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 1908 results — High severity
HIGHEXPLOIT AVAIL

Flowise: SSRF bypass exposes cloud metadata credentials

CVE-2026-67620
7.7
EPSS 0.5%
Data LeakageAuth BypassAgentFramework
flowiseCWE-9183 ATLAS
HIGH

Plesk Obsidian: authenticated SQLi exposes panel DB

CVE-2026-64636
7.7
EPSS 0.4%
Data ExtractionData LeakageFramework
HIGHEXPLOIT AVAIL

Flowise: auth bypass triggers unauthorized OAuth refresh

CVE-2026-70636
7.5
EPSS 0.7%
Auth BypassDoSAgentPlugin
FlowiseCWE-8622 ATLAS
HIGHEXPLOIT AVAIL

Flowise: broken authz lets viewers poison RAG stores

CVE-2026-67621
7.6
EPSS 0.4%
Auth BypassModel PoisoningRAGAgent
FlowiseCWE-8623 ATLAS
HIGH

Traefik: underscore header bypass spoofs identity

CVE-2026-54763
--
EPSS 0.2%
Auth BypassAPI
github.com/traefik/traefik/v3Patch: 3.6.22CWE-1786.3K1 ATLAS
HIGH

llama.cpp: UAF race in tokenize endpoints risks RCE

CVE-2026-43632
8.1
EPSS 0.5%
DoSCode ExecutionInferenceAPI
3 ATLAS
HIGH

Apache CXF: JAX-RS form parameter flood enables DoS

CVE-2026-57819
7.5
EPSS 0.7%
DoSFrameworkAPI
CWE-4003 ATLAS
HIGHEXPLOIT AVAIL

Milvus: unauthenticated DoS via /management/stop

CVE-2026-69111
7.5
EPSS 1.1%
Auth BypassDoSRAGAPI
milvusCWE-30672 ATLAS
HIGH

Livebook: auth fail-open grants full server access

CVE-2026-68746
8.8
EPSS 0.8%
Auth BypassCode ExecutionFramework
2 ATLAS
HIGHEXPLOIT AVAIL

Livebook: path traversal in notebooks writes any file

CVE-2026-66881
8.1
EPSS 0.6%
Code ExecutionSocial EngineeringSupply ChainFramework
2 ATLAS
HIGH

Livebook: sandboxed JS bypasses origin check, forces exec

CVE-2026-66298
8.8
EPSS 0.3%
Code ExecutionDoSFrameworkPlugin
2 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: SSRF bypass in web_crawl via TOCTOU/rebinding

CVE-2026-55524
7.5
EPSS 0.2%
Auth BypassData LeakageAgentPlugin
praisonaiagentsPatch: 1.6.58CWE-367204 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: SSRF via redirect bypass in web_crawl()

CVE-2026-55523
--
EPSS 0.5%
Data LeakageAuth BypassAgentPluginFramework
praisonaiagentsPatch: 1.6.58CWE-918203 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: RCE via workflow include bypasses safe loader

CVE-2026-55522
7.8
EPSS 0.2%
Code ExecutionSupply ChainAgentPluginFramework
PraisonAIPatch: 4.6.58CWE-9414 ATLAS
HIGH

Langflow: truncated-hash bypass enables RCE

CVE-2026-9201
8.8
EPSS 0.4%
Auth BypassCode ExecutionFrameworkAgentPlugin
langflowCWE-3263 ATLAS
HIGH

Langflow: RCE via unapproved LLM-generated code execution

CVE-2026-9196
8.8
EPSS 0.5%
Code ExecutionData LeakageFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: authz bypass leaks cross-user chat history

CVE-2026-9130
7.1
EPSS 0.3%
Auth BypassData LeakagePrivacy ViolationFrameworkAgent
langflow3 ATLAS
HIGH

Langflow: RCE via arbitrary code injection (CWE-94)

CVE-2026-8478
8.8
EPSS 0.6%
Code ExecutionFrameworkAgent
langflowCWE-942 ATLAS
HIGH

Langflow: path traversal exposes arbitrary files

CVE-2026-8183
7.7
EPSS 0.6%
Data ExtractionPrivacy ViolationFramework
langflowCWE-223 ATLAS
HIGH

Langflow: pre-auth RCE via chained HTTP requests

CVE-2026-8182
8.8
EPSS 0.7%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-943 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