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 983 results — Medium severity, no patch
MEDIUM

n8n: unsigned Zendesk webhook allows workflow forgery

CVE-2026-56360
4.0
EPSS 0.3%
Auth BypassAgentPlugin
n8n163 ATLAS
MEDIUM

n8n: XSS via malicious OAuth2 Authorization URL

CVE-2026-56359
5.4
EPSS 0.2%
Code ExecutionSocial EngineeringData LeakageAgentFramework
n8nCWE-79163 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: path traversal in vector store basePath

CVE-2026-56273
6.5
EPSS 0.5%
Code ExecutionFrameworkAgentRAG
flowiseCWE-222 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: blind SSRF via image-edit URL fetch

CVE-2026-34225
4.3
EPSS 0.3%
Privacy ViolationAPIPlugin
open-webuiCWE-91822 ATLAS
MEDIUM

OpenAI Codex: prompt injection exfils data via images

CVE-2026-14898
6.5
EPSS 0.4%
Prompt InjectionData LeakageAgentAPI
4 ATLAS
MEDIUM

OP-TEE: off-by-one in SHA-3 CE overflows TEE kernel heap

CVE-2026-40257
5.5
EPSS 0.2%
DoSCode ExecutionInferenceModel
CWE-7871 ATLAS
MEDIUM

LangSmith SDK: arbitrary file read via TracingMiddleware

CVE-2026-59152
5.0
EPSS 0.2%
Data LeakageAuth BypassFrameworkAgent
langsmith-sdk3.2K3 ATLAS
MEDIUMEXPLOIT AVAIL

ONNX: OOB read in shape inference parsing untrusted models

CVE-2026-14647
4.3
EPSS 0.4%
Code ExecutionDoSModelFramework
onnxCWE-1191.1K2 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: IDOR cross-tenant data pollution

CVE-2026-58653
4.3
EPSS 0.3%
Auth BypassAgentAPI
praisonai12 ATLAS
MEDIUM

Craft CMS: entry section permission bypass

CVE-2026-50280
--
EPSS 0.4%
Auth BypassPlugin
MEDIUM

Kibana: sensitive headers leaked via APM logs

CVE-2026-49088
4.4
EPSS 0.3%
Data LeakagePrivacy ViolationAPI
MEDIUM

n8n: AST validator bypass leaks env vars in Python node

CVE-2026-56777
5.0
EPSS 0.3%
Code ExecutionData LeakageAgentPlugin
n8nCWE-184164 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: SSRF in web retrieval hits internal services

CVE-2026-56399
5.0
EPSS 0.5%
Auth BypassCode ExecutionData LeakageRAGAPI
open-webui23 ATLAS
MEDIUM

n8n: stored XSS in Chat Trigger Custom CSS field

CVE-2026-56356
5.4
EPSS 0.3%
Code ExecutionSocial EngineeringAgentPlugin
n8nCWE-79162 ATLAS
MEDIUM

n8n: authenticated users can disable SSO enforcement via API

CVE-2026-56350
6.3
EPSS 0.4%
Auth BypassAgentFramework
n8nCWE-285163 ATLAS
MEDIUM

Langflow: SSRF via DNS rebinding in URL component

CVE-2026-10546
6.5
EPSS 0.2%
Data LeakageCode ExecutionFrameworkAgent
langflowCWE-9182 ATLAS
MEDIUM

Sigstore TSA: unbounded metrics label DoS

CVE-2026-49835
5.9
EPSS 0.7%
DoSAPI
github.com/sigstore/timestamp-authorityCWE-7702 ATLAS
MEDIUM

GLib: D-Bus cookie path traversal leaks local files

CVE-2026-58015
5.9
EPSS 0.8%
Data LeakageData ExtractionInferenceFramework
rhaiis/vllm-cuda-rhel9942 ATLAS
MEDIUM

GLib: buffer over-read in line reader causes DoS

CVE-2026-58013
6.5
EPSS 0.5%
DoSData LeakageInferenceFramework
rhaiis/vllm-cuda-rhel9942 ATLAS
MEDIUM

GLib: g_regex_replace RAW over-read leaks bytes, DoS

CVE-2026-58012
6.5
EPSS 0.5%
DoSData LeakageInferenceFramework
rhaiis/vllm-cuda-rhel9942 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