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
HIGH

Crabbox: path traversal enables arbitrary file wipe

CVE-2026-45224
7.1
EPSS 0.1%
Supply ChainDoSAgent
crabbox33 ATLAS
HIGHEXPLOIT AVAIL

Crabbox: coordinator auth bypass via forged admin claim

CVE-2026-45223
8.8
EPSS 0.4%
Auth BypassAgent
crabbox34 ATLAS
HIGH

flash-attention: RCE via unsafe checkpoint deserialization

CVE-2026-31253
7.3
EPSS 0.2%
Code ExecutionSupply ChainFrameworkTraining Data
flash_attnCWE-9426.1K4 ATLAS
UNKNOWN

CosyVoice: RCE via unsafe torch.load() deserialization

CVE-2026-31252
--
EPSS 0.1%
Supply ChainCode ExecutionModelFramework
5 ATLAS
UNKNOWN

CosyVoice: RCE via unsafe torch.load() deserialization

CVE-2026-31251
--
EPSS 0.2%
Supply ChainCode ExecutionModelInference
4 ATLAS
UNKNOWN

CosyVoice: RCE via unsafe torch.load() in model averaging

CVE-2026-31250
--
EPSS 0.2%
Supply ChainCode ExecutionModelTraining Data
4 ATLAS
UNKNOWN

CosyVoice: insecure deserialization RCE via .pt files

CVE-2026-31249
--
EPSS 0.2%
Code ExecutionSupply ChainTraining DataModel
3 ATLAS
HIGHEXPLOIT AVAIL

BentoML: Dockerfile injection enables build-time RCE

CVE-2026-44346
8.8
EPSS 0.3%
Supply ChainCode ExecutionFrameworkInference
bentomlPatch: 1.4.39CWE-78235 ATLAS
HIGHEXPLOIT AVAIL

BentoML: unsanitized base_image allows Dockerfile RCE

CVE-2026-44345
8.8
EPSS 0.3%
Supply ChainCode ExecutionFramework
bentomlPatch: 1.4.39CWE-78234 ATLAS
HIGHEXPLOIT AVAIL

open-webui: IDOR exposes cross-user AI memory data

CVE-2026-44570
8.3
EPSS 0.3%
Auth BypassData ExtractionPrivacy ViolationAPIAgent
open-webuiPatch: 0.6.19CWE-63925 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: auth bypass allows message tampering

CVE-2026-44571
6.5
EPSS 0.3%
Auth BypassPrompt InjectionAPIFramework
open-webuiPatch: 0.8.6CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: IDOR enables cross-user message tampering

CVE-2026-44569
7.1
EPSS 0.3%
Auth BypassAPIFramework
open-webuiPatch: 0.6.19CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

open-webui: path traversal enables file write/delete

CVE-2026-44565
8.1
EPSS 0.5%
Code ExecutionDoSInferenceFramework
open-webuiPatch: 0.6.10CWE-2225 ATLAS
HIGH

open-webui: CORS misconfiguration enables 1-click RCE

GHSA-6xcp-7mpr-m7wm
8.3
Code ExecutionAuth BypassFrameworkInference
open-webuiPatch: 0.3.33CWE-61325 ATLAS1 incident
HIGH

PraisonAI: tar symlink bypass allows arbitrary file write

CVE-2026-44340
7.5
EPSS 0.4%
Supply ChainCode ExecutionAgentFramework
PraisonAIPatch: 4.6.37CWE-2215 ATLAS1 incident
HIGHEXPLOIT AVAIL

praisonaiagents: tool bypass enables undeclared callable exec

CVE-2026-44339
8.6
EPSS 0.4%
Code ExecutionAuth BypassAgentFramework
PraisonAIPatch: 4.6.37CWE-47015 ATLAS1 incident
CRITICALEXPLOIT AVAIL

PraisonAI: MCP path traversal escalates to full RCE

CVE-2026-44336
9.6
EPSS 0.6%
Prompt InjectionCode ExecutionData ExtractionAgentPluginFramework
PraisonAIPatch: 4.6.34CWE-2018 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: SQL/CQL injection in knowledge-store backends

CVE-2026-44337
6.3
EPSS 0.2%
Code ExecutionData ExtractionData LeakageAgentRAGFramework
PraisonAIPatch: 4.6.34CWE-2015 ATLAS
HIGHEXPLOIT AVAILSCANNER

PraisonAI: unauthenticated API triggers agent workflows

CVE-2026-44338
7.3
EPSS 32.6%
Auth BypassCode ExecutionDoSAgentFramework
PraisonAIPatch: 4.6.34CWE-30617 ATLAS
MEDIUMEXPLOIT AVAIL

Videos sync PDF: stored XSS via unsanitized media fields

CVE-2022-50949
6.4
EPSS 0.2%
Code ExecutionPlugin

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