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
2,390

AI/ML CVEs Tracked

342

Critical

360

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 1564 results — no patch
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
HIGH

A flaw was found in the libssh library in versions less than 0.11.2. An out-of-bounds read can be triggered in the sftp_handle function due to an incorrect...

CVE-2025-5318
8.1
rhaiis/vllm-cuda-rhel9 130
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
HIGH

Hive Support WP: OpenAI key theft + prompt hijack

CVE-2025-5018
7.1
EPSS 0.3%
Auth Bypass Data Extraction Prompt Injection API Plugin
6 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: input validation DoS crashes inference worker

CVE-2025-48944
6.5
EPSS 0.4%
DoS Inference API Framework
vllm CWE-20 130 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: ReDoS crashes inference server via malformed regex

CVE-2025-48943
6.5
EPSS 0.4%
DoS Inference Framework
vllm CWE-248 130 4 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: DoS via malformed JSON schema guided param

CVE-2025-48942
6.5
EPSS 0.5%
DoS Inference API
vllm CWE-248 130 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: ReDoS in tool parser causes service outage

CVE-2025-48887
6.5
EPSS 0.4%
DoS Inference API Framework
vllm CWE-1333 130 3 ATLAS
HIGH EXPLOIT AVAIL

Gradio: unauthenticated file copy enables disk DoS

CVE-2025-48889
7.5
EPSS 0.6%
DoS Framework Inference
gradio CWE-434 685 3 ATLAS
HIGH

vLLM: image hash collision enables multimodal cache leakage

CVE-2025-46722
7.3
EPSS 0.3%
Data Leakage Privacy Violation Inference Framework
vllm CWE-1023 130 4 ATLAS
LOW

vLLM: timing side-channel leaks prompt cache data

CVE-2025-46570
2.6
EPSS 0.2%
Privacy Violation Data Extraction Inference Framework
vllm CWE-203 130 4 ATLAS
LOW EXPLOIT AVAIL

Gradio: CORS origin bypass in ML UI handler

CVE-2025-5320
3.7
EPSS 0.2%
Auth Bypass Framework Inference
gradio CWE-345 685 3 ATLAS
HIGH EXPLOIT AVAIL

llama-index-cli: OS command injection enables RCE

CVE-2025-1753
7.8
EPSS 1.0%
Code Execution Supply Chain Framework Agent
llama-index CWE-78 238 4 ATLAS
HIGH

label-studio-ml: PyTorch .pt deserialization RCE in YOLO loader

CVE-2025-5173
7.8
EPSS 0.2%
Supply Chain Code Execution Framework Model
label-studio-ml CWE-502 1 4 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
HIGH EXPLOIT AVAIL

transformers: ReDoS in testing_utils causes DoS

CVE-2025-2099
7.5
EPSS 0.5%
DoS Framework
transformers CWE-1333 8.3K 3 ATLAS
UNKNOWN EXPLOIT AVAIL

Ollama: DoS via malicious manifest in /api/pull

CVE-2025-1975
--
EPSS 0.4%
DoS Inference API
ollama 1.6K 3 ATLAS
HIGH

TensorFlow Serving: JSON recursion DoS on inference API

CVE-2025-0649
7.5
EPSS 0.2%
DoS Inference API Framework
tensorflow_serving CWE-787 3.7K 3 ATLAS
HIGH

vLLM: pickle RCE in multi-node inference deployments

CVE-2025-30165
8.0
EPSS 0.5%
Code Execution Inference Framework
vllm CWE-502 130 3 ATLAS
LOW EXPLOIT AVAIL

PyTorch NCCL: local DoS in distributed training reduce op

CVE-2025-4287
3.3
EPSS 0.1%
DoS Framework Training Data
3 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