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
3,631

AI/ML CVEs Tracked

484

Critical

99

New This Week

25

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1044 results — High severity, no patch
HIGH

NVIDIA Transformers4Rec: deserialization RCE

CVE-2026-24162
7.8
EPSS 0.4%
Code Execution Supply Chain Data Extraction Framework Model
CWE-502 4 ATLAS
HIGH

389-ds-base: LDAP DoS via unbounded control count

CVE-2026-9064
7.5
EPSS 0.8%
DoS Framework
3 ATLAS
HIGH

gnutls: DTLS packet-reorder bug DoS hits AI inference servers

CVE-2026-42009
7.5
EPSS 1.3%
DoS Inference
rhaiis/vllm-rocm-rhel9 92 2 ATLAS
HIGH EXPLOIT AVAIL

Bert-VITS2: path traversal exposes ML training filesystem

CVE-2026-8756
7.3
EPSS 0.5%
Data Extraction Code Execution Framework Training Data
CWE-22 4 ATLAS
HIGH EXPLOIT AVAIL

Crabbox: IDOR lets viewers hijack Code/VNC/Egress

CVE-2026-8629
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent
crabbox 3 3 ATLAS
HIGH

Crabbox: header spoofing bypasses lease auth

CVE-2026-8621
8.8
EPSS 0.4%
Auth Bypass Privacy Violation Agent API
crabbox 3 3 ATLAS
HIGH EXPLOIT AVAIL

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

CVE-2026-44246
7.2
EPSS 0.2%
Prompt Injection Code Execution Agent Plugin
claude-code 5 ATLAS
HIGH

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

CVE-2026-31232
8.8
EPSS 0.5%
Supply Chain Code Execution Model Inference
5 ATLAS
HIGH

snorkel: RCE via unsafe model deserialization

CVE-2026-31224
8.8
EPSS 0.4%
Supply Chain Code Execution Model Framework
snorkel CWE-502 25.2K 4 ATLAS
HIGH

snorkel: RCE via insecure model checkpoint loading

CVE-2026-31222
8.8
EPSS 0.4%
Code Execution Supply Chain Model Training Data
snorkel CWE-502 25.2K 4 ATLAS
HIGH

pytorch-lightning: RCE via insecure checkpoint deserialization

CVE-2026-31221
7.8
EPSS 0.4%
Supply Chain Code Execution Framework Model
pytorch-lightning CWE-502 1.7K 4 ATLAS
HIGH

Crabbox: path traversal enables arbitrary file wipe

CVE-2026-45224
7.1
EPSS 0.1%
Supply Chain DoS Agent
crabbox 3 3 ATLAS
HIGH EXPLOIT AVAIL

Crabbox: coordinator auth bypass via forged admin claim

CVE-2026-45223
8.8
EPSS 0.4%
Auth Bypass Agent
crabbox 3 4 ATLAS
HIGH

flash-attention: RCE via unsafe checkpoint deserialization

CVE-2026-31253
7.3
EPSS 0.2%
Code Execution Supply Chain Framework Training Data
flash_attn CWE-94 25.2K 4 ATLAS
HIGH KEV SCANNER

LiteLLM: RCE via MCP test endpoint command injection

CVE-2026-42271
8.8
EPSS 83.6%
Code Execution Auth Bypass Framework API Inference
litellm CWE-77 6 5 ATLAS
HIGH

LiteLLM: SSTI in prompt template endpoint enables RCE

CVE-2026-42203
8.8
EPSS 0.4%
Code Execution Data Extraction API Inference
litellm CWE-1336 6 5 ATLAS
HIGH

gnutls: NUL-byte username bypasses RSA-PSK auth

CVE-2026-42010
7.1
EPSS 1.1%
Auth Bypass Inference
rhaiis/vllm-rocm-rhel9 92 3 ATLAS
HIGH

GnuTLS: DTLS fragment heap overflow, DoS on AI inference

CVE-2026-33846
7.5
EPSS 1.3%
DoS Code Execution Inference
rhaiis/vllm-rocm-rhel9 92 2 ATLAS
HIGH

Langflow: RCE exposes API keys and DB credentials

CVE-2026-6543
8.8
EPSS 0.5%
Code Execution Data Extraction Supply Chain Framework Agent
langflow CWE-94 5 ATLAS
HIGH

Langflow: IDOR exposes cross-tenant flow data and deletion

CVE-2026-6542
8.1
EPSS 0.2%
Data Extraction Privacy Violation Auth Bypass Framework Agent
langflow CWE-639 5 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