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
HIGHEXPLOIT AVAIL

Flowise: mass assignment breaks multi-tenant isolation

CVE-2026-42861
--
EPSS 0.3%
Auth BypassData ExtractionAgentFramework
flowisePatch: 3.1.2CWE-2844 ATLAS
HIGHEXPLOIT AVAIL

claude-code-cache-fix: hook path injection → RCE

CVE-2026-45136
--
EPSS 0.2%
Code ExecutionSupply ChainAgentPlugin
claude-code-cache-fixPatch: 3.5.2CWE-785 ATLAS
HIGH

LangSmith: prompt deserialization enables SSRF + data leak

CVE-2026-45134
7.1
EPSS 0.2%
Supply ChainData ExtractionData LeakageFrameworkAgentAPI
langchainPatch: 0.3.30CWE-5023.2K5 ATLAS
HIGHEXPLOIT AVAIL

nnU-Net: prompt injection hijacks CI/CD triage agent

CVE-2026-44246
7.2
EPSS 0.3%
Prompt InjectionCode ExecutionAgentPlugin
claude-code5 ATLAS
CRITICAL

guardrails-ai: RCE via malicious Hub package manifest

CVE-2026-31233
9.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkPlugin
guardrails-aiCWE-94785 ATLAS
CRITICAL

mamba: RCE via unsafe torch.load() on model load

CVE-2026-31239
9.8
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
mamba-ssmCWE-50226.1K5 ATLAS
CRITICAL

Ludwig: RCE via unsafe pickle deserialization in model serve

CVE-2026-31238
9.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkModelInference
ludwigCWE-50226.1K4 ATLAS
HIGH

CosyVoice: RCE via unsafe torch.load() model deserialization

CVE-2026-31232
8.8
EPSS 0.5%
Supply ChainCode ExecutionModelInference
5 ATLAS
CRITICAL

ART: torch.load() RCE via insecure deserialization

CVE-2026-31229
9.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkModel
4 ATLAS
CRITICALEXPLOIT AVAIL

openclaude: sandbox bypass allows host-level RCE

CVE-2026-42074
--
EPSS 0.6%
Prompt InjectionCode ExecutionAuth BypassAgentFrameworkPlugin
openclaudePatch: 0.5.1CWE-2846.3K6 ATLAS
HIGH

snorkel: RCE via unsafe model deserialization

CVE-2026-31224
8.8
EPSS 0.4%
Supply ChainCode ExecutionModelFramework
snorkelCWE-50226.1K4 ATLAS
HIGH

snorkel: RCE via insecure model checkpoint loading

CVE-2026-31222
8.8
EPSS 0.4%
Code ExecutionSupply ChainModelTraining Data
snorkelCWE-50226.1K4 ATLAS
HIGH

pytorch-lightning: RCE via insecure checkpoint deserialization

CVE-2026-31221
7.8
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
pytorch-lightningCWE-5021.7K4 ATLAS
UNKNOWN

optimate: RCE via unsafe torch.load() deserialization

CVE-2026-31219
--
EPSS 0.6%
Supply ChainCode ExecutionModelTraining Data
4 ATLAS
UNKNOWN

optimate: unsafe torch.load() enables RCE via model file

CVE-2026-31218
--
EPSS 0.6%
Supply ChainCode ExecutionModelTraining Data
4 ATLAS
CRITICAL

torch-checkpoint: unsafe pickle deserialization RCE

CVE-2026-31214
9.8
EPSS 0.5%
Code ExecutionSupply ChainModelTraining Data
4 ATLAS
HIGHEXPLOIT AVAILSCANNER

MLflow: path traversal allows unauthenticated file read

CVE-2026-2614
7.5
EPSS 3.7%
Auth BypassData ExtractionFrameworkTraining Data
mlflowPatch: 3.10.0CWE-226955 ATLAS
MEDIUMEXPLOIT AVAIL

local-deep-research: HTML injection enables SSRF via WeasyPrint

CVE-2026-43979
5.0
EPSS 0.3%
Data ExtractionDoSFrameworkAPI
local-deep-researchPatch: 1.6.0CWE-791.9K4 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: SSRF in agent tools bypasses security wrapper

CVE-2026-43995
9.8
EPSS 0.4%
Code ExecutionData ExtractionAuth BypassAgentFrameworkPlugin
flowise5 ATLAS
HIGHEXPLOIT AVAIL

MLflow: SSRF in webhook URL enables cloud credential theft

CVE-2026-2393
7.1
EPSS 0.3%
Data ExtractionAuth BypassFramework
mlflowPatch: 3.9.0CWE-9186954 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