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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1527 results — Medium severity
MEDIUM

Gradio: arbitrary file upload via /upload endpoint

CVE-2023-41626
4.8
EPSS 0.4%
Code ExecutionData ExtractionSupply ChainFrameworkInference
gradioCWE-4347354 ATLAS
MEDIUM

Azure HDInsight: Jupyter Notebook XSS enables spoofing

CVE-2023-35394
4.6
EPSS 1.0%
Social EngineeringData LeakageFramework
MEDIUMEXPLOIT AVAIL

ChuanhuChatGPT: config exposure leaks API keys

CVE-2023-34094
5.3
EPSS 0.6%
Data ExtractionAuth BypassFrameworkAPI
chuanhuchatgptCWE-3064 ATLAS
MEDIUMEXPLOIT AVAIL

Transformers: temp file race condition allows local DoS

CVE-2023-2800
4.7
EPSS 0.3%
DoSSupply ChainFrameworkTraining Data
transformersCWE-3779.8K3 ATLAS
MEDIUMEXPLOIT AVAIL

n8n: path traversal allows arbitrary file read

CVE-2023-27562
6.5
EPSS 2.3%
Data ExtractionAuth BypassAgentFramework
n8nCWE-22165 ATLAS
MEDIUMEXPLOIT AVAIL

AI ChatBot WP: auth bypass exposes OpenAI config + XSS

CVE-2023-1651
5.4
EPSS 0.2%
Auth BypassData LeakageCode ExecutionPluginAPI
wpbot5 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via malformed Convolution3D input

CVE-2023-25661
6.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUM

Streamlit: reflected XSS enables session hijacking

CVE-2023-27494
6.1
EPSS 0.4%
Code ExecutionData LeakageFramework
streamlit3.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

Label Studio: SSRF + file read, self-reg bypass

CVE-2022-36551
6.5
EPSS 6.9%
Data ExtractionAuth BypassData LeakageTraining DataFramework
label-studioPatch: 1.6.0CWE-91826 ATLAS
MEDIUM

Streamlit: path traversal leaks server filesystem

CVE-2022-35918
6.5
EPSS 1.8%
Data ExtractionData LeakageFramework
streamlitCWE-223.1K5 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: input validation DoS in FFT signal ops

CVE-2022-29213
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow Lite: quantization assert crash (DoS)

CVE-2022-29212
5.5
EPSS 0.3%
DoSSupply ChainFrameworkInferenceModel
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: NaN input crashes histogram op (CPU DoS)

CVE-2022-29211
5.5
EPSS 0.3%
DoSFrameworkTraining Data
tensorflow3.4K4 ATLAS
MEDIUM

TensorFlow: heap OOB in TensorKey causes DoS

CVE-2022-29210
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflowCWE-7873.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: CHECK macro type confusion causes DoS

CVE-2022-29209
5.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: SparseTensorDenseAdd null ptr deref DoS

CVE-2022-29206
5.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: NULL deref DoS via compat.v1 ops

CVE-2022-29205
5.5
EPSS 0.3%
DoSFramework
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via UnsortedSegmentJoin input validation

CVE-2022-29204
5.5
EPSS 0.4%
DoSFramework
tensorflowCWE-203.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via SpaceToBatchND integer overflow

CVE-2022-29203
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via ragged tensor memory exhaustion

CVE-2022-29202
5.5
EPSS 0.3%
DoSFramework
tensorflowCWE-12843.4K3 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