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
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4330 results
MEDIUM

Keras: HDF5 ExternalLink flaw leaks local files on load

CVE-2026-9335
6.5
EPSS 0.8%
Data LeakageSupply ChainFrameworkModel
kerasPatch: 3.12.3CWE-224.1K3 ATLAS
MEDIUM

JupyterLab: stored XSS via malicious extension metadata

CVE-2026-67338
6.1
EPSS 0.3%
Supply ChainCode ExecutionSocial EngineeringPlugin
CWE-843 ATLAS
CRITICAL

ComfyUI: unauthenticated RCE via pickle upload

CVE-2026-68771
9.8
EPSS 1.1%
Code ExecutionSupply ChainTraining DataFramework
CWE-5024 ATLAS
CRITICALEXPLOIT AVAIL

sentence-transformers: trust gate bypass enables RCE

CVE-2026-68770
9.8
EPSS 0.9%
Auth BypassCode ExecutionSupply ChainModelInferenceFramework
sentence-transformersPatch: 5.6.0CWE-943.1K4 ATLAS
HIGH

Pterodactyl Wings: SFTP handshake DoS via Go panic

CVE-2026-52856
7.5
EPSS 0.6%
DoSFramework
CWE-129
CRITICAL

Pterodactyl Wings: egg template leaks daemon secrets

CVE-2026-52855
9.9
EPSS 0.5%
Data LeakageAuth BypassPlugin
github.com/pterodactyl/wingsPatch: 1.12.3CWE-2005141 ATLAS
MEDIUM

Pterodactyl Wings: config parser DoS exhausts memory

CVE-2026-52857
5.5
EPSS 0.2%
DoS
MEDIUM

pgAdmin: broken access control bypasses tool permissions

CVE-2026-17350
5.4
EPSS 0.4%
Auth BypassCode ExecutionRAG
1 ATLAS
HIGH

Dynatrace MCP server: unauth HTTP data exfil via DQL

GHSA-p7w7-4929-vpj5
7.5
Auth BypassData LeakageData ExtractionAgentPluginAPI
@dynatrace-oss/dynatrace-mcp-serverPatch: 2.0.0CWE-3063.0K3 ATLAS
MEDIUM

Dynatrace MCP: Jinja injection creates persistent exfil

GHSA-xrmj-5g4g-8987
4.2
Prompt InjectionData LeakageCode ExecutionAgentPluginAPI
CWE-13363 ATLAS
MEDIUM

Dynatrace MCP server: DQL injection bypasses read-tool caps

GHSA-pqh8-p93p-2rx7
4.3
Prompt InjectionData LeakageAuth BypassAgentPluginAPI
CWE-9433 ATLAS
MEDIUM

Apache Zeppelin: path traversal escapes notebook root

CVE-2026-44615
6.5
EPSS 0.8%
Code ExecutionDoSFramework
CWE-222 ATLAS
HIGH

Google mcp-toolbox: BigQuery allowedDatasets bypass

CVE-2026-14538
7.7
EPSS 0.2%
Auth BypassData ExtractionData LeakageAgentPluginAPI
3 ATLAS
CRITICALEXPLOIT AVAIL

OpenClaw Dashboard: stored XSS enables admin takeover

CVE-2026-66421
9.3
EPSS 0.6%
Code ExecutionAuth BypassData LeakageAgentFramework
openclaw-dashboardCWE-7933 ATLAS
HIGH

MeshCentral: origin-check bypass lets attackers hijack admin sessions

CVE-2026-66420
8.8
EPSS 0.2%
Auth BypassData LeakageCode ExecutionAgent
openclaw-dashboard34 ATLAS
CRITICALEXPLOIT AVAIL

OpenClaw: stored XSS via login field hijacks admin

CVE-2026-66418
9.3
EPSS 0.6%
Code ExecutionAuth BypassAgentFramework
openclawCWE-7933 ATLAS
CRITICALEXPLOIT AVAIL

amplify-codegen-ui: eval injection enables build-time RCE

CVE-2025-4318
--
EPSS 1.0%
Code ExecutionSupply ChainFramework
@aws-amplify/codegen-ui-reactPatch: 2.20.3CWE-956422 ATLAS
CRITICAL

Langflow: unsanitized code input enables RCE

CVE-2026-12946
9.9
EPSS 0.6%
Code ExecutionAuth BypassFrameworkAgent
langflow2 ATLAS
CRITICALEXPLOIT AVAIL

SGLang: RCE via unsafe pickle deserialization on weight load

CVE-2026-15976
9.8
EPSS 0.6%
Code ExecutionSupply ChainInferenceModelFramework
4 ATLAS
HIGH

Langflow: IDOR exposes/poisons cross-tenant RAG vectors

CVE-2026-13444
8.1
EPSS 0.4%
Auth BypassData LeakagePrivacy ViolationFrameworkRAGPlugin
langflowCWE-5203 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