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
2,387

AI/ML CVEs Tracked

341

Critical

358

New This Week

18

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 230 results — Critical severity, no patch
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated SSRF via file upload URLs

CVE-2025-54381
9.9
EPSS 11.1%
Supply Chain Data Extraction Auth Bypass Framework Inference API
bentoml CWE-918 21 5 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain GmailToolkit: indirect prompt injection to RCE

CVE-2025-46059
9.8
EPSS 0.7%
Prompt Injection Code Execution Data Extraction Framework Agent Plugin
6 ATLAS
CRITICAL EXPLOIT AVAIL

smolagents: sandbox escape enables unauthenticated RCE

CVE-2025-5120
10.0
EPSS 17.7%
Code Execution Supply Chain Data Leakage Framework Agent
smolagents CWE-94 93 5 ATLAS
CRITICAL EXPLOIT AVAIL

Langchain-Chatchat: path traversal in KB upload

CVE-2025-6853
9.8
EPSS 0.5%
Code Execution Data Extraction Supply Chain Framework RAG
langchain-chatchat CWE-22 2.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

LLaMA-Factory: RCE via unsafe checkpoint deserialization

CVE-2025-53002
9.8
EPSS 1.0%
Code Execution Supply Chain Framework Model
llamafactory CWE-94 1 6 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain RequestsToolkit: SSRF exposes cloud metadata

CVE-2025-2828
10.0
EPSS 14.1%
Data Extraction Auth Bypass Framework Agent
langchain CWE-918 2.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

vLLM: RCE via exposed TCPStore in distributed inference

CVE-2025-47277
9.8
EPSS 0.9%
Code Execution Data Extraction Inference Framework
vllm CWE-502 130 4 ATLAS
CRITICAL EXPLOIT AVAIL

vLLM: RCE via pickle deserialization on ZeroMQ

CVE-2025-32444
9.8
EPSS 1.5%
Code Execution Supply Chain Inference Framework
vllm CWE-502 130 5 ATLAS
CRITICAL EXPLOIT AVAIL

PyTorch: RCE bypasses weights_only=True safe-load guard

CVE-2025-32434
9.8
EPSS 1.9%
Code Execution Supply Chain Framework Model Inference
pytorch CWE-502 22.7K 6 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: RCE via insecure deserialization in runner

CVE-2025-32375
9.8
EPSS 43.8%
Code Execution Data Extraction Supply Chain Framework Inference
bentoml CWE-502 21 5 ATLAS
CRITICAL KEV SCANNER

Langflow: Unauth RCE via code injection endpoint

CVE-2025-3248
9.8
EPSS 100.0%
Code Execution Auth Bypass Framework Agent
langflow CWE-94 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via insecure deserialization

CVE-2025-27520
9.8
EPSS 43.7%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 21 5 ATLAS
CRITICAL

vLLM: RCE via pickle deserialization in distributed API

CVE-2024-9052
9.8
EPSS 0.3%
Code Execution Supply Chain Framework Inference
vllm CWE-502 130 3 ATLAS
CRITICAL EXPLOIT AVAIL

llama-index finchat: SQL injection enables RCE

CVE-2024-12909
10.0
EPSS 1.3%
Code Execution Supply Chain Data Extraction Agent Framework Plugin
llama-index-packs-finchat CWE-89 238 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via runner deserialization

CVE-2024-9070
9.8
EPSS 0.8%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 21 3 ATLAS
CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in RPC server

CVE-2024-9053
9.8
EPSS 1.3%
Code Execution Supply Chain Framework Inference
vllm CWE-78 130 5 ATLAS
CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in MessageQueue

CVE-2024-11041
9.8
EPSS 1.4%
Code Execution Framework Inference
vllm CWE-502 130 4 ATLAS
CRITICAL EXPLOIT AVAIL

vLLM: RCE via unsafe deserialization in Mooncake KV

CVE-2025-29783
9.0
EPSS 0.8%
Code Execution Supply Chain Framework Inference
vllm CWE-502 130 5 ATLAS
CRITICAL EXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model loading

CVE-2025-1550
9.8
EPSS 2.8%
Code Execution Supply Chain Framework Model
keras CWE-94 1.6K 6 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: ZIP flag bypass enables RCE in PyTorch models

CVE-2025-1945
9.8
EPSS 0.5%
Supply Chain Code Execution Model Framework
picklescan CWE-345 3 6 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