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 943 results — High severity, Active exploitation
HIGHEXPLOIT AVAIL

litellm: auth bypass in Admin Key Handler endpoint

CVE-2026-12770
8.8
EPSS 0.6%
Auth BypassDoSInferenceAPI
litellmCWE-26664 ATLAS
HIGHEXPLOIT AVAIL

vLLM: sparse tensor DoS/memory corruption via embeddings

CVE-2026-56340
7.5
EPSS 0.6%
DoSCode ExecutionInferenceAPI
vllmCWE-20945 ATLAS
HIGHEXPLOIT AVAIL

Langflow: pre-auth DoS via malformed multipart boundary

CVE-2026-55446
7.5
EPSS 0.6%
DoSAuth BypassFramework
langflowPatch: 1.0.19CWE-4003 ATLAS
HIGHEXPLOIT AVAIL

jupyterlab-git: excluded_paths bypass exposes secrets

CVE-2026-54528
7.1
EPSS 0.4%
Auth BypassData ExtractionFrameworkPlugin
jupyterlab-gitPatch: 0.54.0CWE-1781.9K5 ATLAS
HIGHEXPLOIT AVAIL

Stanza: pickle fallback bypass enables model RCE

CVE-2026-54499
7.5
EPSS 0.5%
Supply ChainCode ExecutionModelFramework
torchCWE-50226.1K5 ATLAS
HIGHEXPLOIT AVAIL

Home Assistant Konnected: auth bypass leaks alarm panel state

CVE-2026-54317
7.6
EPSS 0.3%
Auth BypassData ExtractionDoSPlugin
homeassistantPatch: 2026.6.0CWE-2005144 ATLAS
HIGHEXPLOIT AVAIL

libaom: AV1 SVC OOB write enables RCE

CVE-2026-56211
7.1
EPSS 0.9%
Code ExecutionSupply ChainInference
rhaiis/vllm-cpu-rhel9942 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: path traversal → arbitrary file read/write/RCE

CVE-2026-56078
8.8
EPSS 0.9%
Code ExecutionData ExtractionAuth BypassAgentFramework
PraisonAICWE-2216 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: CORS bypass enables arbitrary agent execution

CVE-2026-56076
8.1
EPSS 0.6%
Auth BypassData ExtractionCode ExecutionAgentAPIFramework
PraisonAICWE-94216 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: RCE via hardcoded approval_mode bypass

CVE-2026-56075
8.8
EPSS 0.6%
Code ExecutionAuth BypassAgentFramework
PraisonAICWE-86315 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF via redirect bypass in Playwright loader

CVE-2026-54018
7.7
EPSS 0.4%
Auth BypassData ExtractionRAGFramework
open-webuiPatch: 0.9.6CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

open-webui: double-encoded path traversal in terminal proxy

CVE-2026-54017
7.7
EPSS 0.5%
Data ExtractionCode ExecutionFrameworkAgent
open-webuiPatch: 0.9.6CWE-2224 ATLAS
HIGHEXPLOIT AVAIL

picklescan: arbitrary file read bypasses RCE blocklist

CVE-2026-53872
7.5
EPSS 0.5%
Data ExtractionSupply ChainFrameworkModel
picklescan35 ATLAS
HIGHEXPLOIT AVAIL

PickleScan: pty.spawn bypass enables RCE in model scans

CVE-2025-71322
8.8
EPSS 0.4%
Supply ChainCode ExecutionModelFramework
PickleScanCWE-69335 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: stored SVG XSS enables full account takeover

CVE-2026-54013
7.6
EPSS 0.3%
Auth BypassCode ExecutionData ExtractionAPIFramework
open-webuiPatch: 0.9.6CWE-7924 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: auth bypass enables cross-user file read/delete

CVE-2026-54012
7.1
EPSS 0.3%
Auth BypassData ExtractionData LeakageRAGAgentFramework
open-webuiPatch: 0.9.6CWE-28425 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: Stored XSS via Mermaid loose mode in preview

CVE-2026-54011
8.7
EPSS 0.3%
Code ExecutionData ExtractionAuth BypassFrameworkPlugin
open-webuiPatch: 0.9.6CWE-7925 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: IDOR allows cross-user file read and delete

CVE-2026-54010
8.3
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.9.6CWE-28424 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF via OAuth picture redirect bypass

CVE-2026-54008
8.5
EPSS 0.3%
Data ExtractionPrivacy ViolationAPIInference
open-webuiPatch: 0.9.6CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

open-webui: cross-origin postMessage forces model execution

CVE-2026-54007
--
EPSS 0.2%
Prompt InjectionAuth BypassCode ExecutionAPIAgent
open-webuiPatch: 0.9.6CWE-34625 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