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

Better: security flaw enables exploitation

CVE-2025-12360
4.3
EPSS 0.2%
Auth BypassDoSAPIPlugin
6 ATLAS
MEDIUMEXPLOIT AVAIL

dspy: security flaw enables exploitation

CVE-2025-12695
5.9
EPSS 0.3%
Data ExtractionCode ExecutionFrameworkAgent
dspyCWE-653585 ATLAS
MEDIUMEXPLOIT AVAIL

Keras: safe_mode bypass enables file read and SSRF

CVE-2025-12058
--
EPSS 0.2%
Data ExtractionSupply ChainCode ExecutionFrameworkModel
kerasPatch: 3.12.0CWE-5024.1K5 ATLAS
MEDIUMEXPLOIT AVAIL

smolagents: security flaw enables exploitation

CVE-2025-11844
5.4
EPSS 0.3%
Data ExtractionAuth BypassAgentFrameworkPlugin
smolagentsCWE-6431114 ATLAS
MEDIUMEXPLOIT AVAIL

Moodle: IDOR enables unauthorized data access

CVE-2025-60511
4.3
EPSS 0.2%
Auth BypassData LeakageData ExtractionPluginAPI
5 ATLAS
MEDIUM

vllm: DoS via Jinja template injection in chat API

CVE-2025-61620
6.5
EPSS 0.2%
DoSFrameworkInferenceAPI
vllmPatch: 0.11.0CWE-20945 ATLAS
MEDIUMEXPLOIT AVAIL

clearml: path traversal in safe_extract → RCE risk

CVE-2025-8917
5.8
EPSS 0.5%
Supply ChainCode ExecutionFrameworkTraining Data
clearmlPatch: 2.0.2CWE-22234 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: non-deterministic compilation breaks Embedding

CVE-2025-55556
6.5
EPSS 0.2%
Supply ChainDoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: integer overflow in nan_to_num causes DoS

CVE-2025-55554
5.3
EPSS 0.3%
DoSSupply ChainFrameworkInference
pytorch26.1K3 ATLAS
MEDIUM

PyTorch: Dropout inconsistency enables membership inference

CVE-2025-46153
5.3
EPSS 0.4%
Data ExtractionPrivacy ViolationFrameworkInferenceTraining Data
pytorch26.1K3 ATLAS
MEDIUM

PyTorch: OOB write causes incorrect bitwise shift results

CVE-2025-46152
5.3
EPSS 0.5%
Supply ChainDoSFrameworkTraining DataInference
pytorch26.1K3 ATLAS
MEDIUM

PyTorch: torch.compile silent output inconsistency

CVE-2025-46150
5.3
EPSS 0.4%
Adversarial ExamplesSupply ChainFrameworkInferenceModel
pytorch26.1K4 ATLAS
MEDIUM

PyTorch: reachable assertion in nn.Fold with inductor

CVE-2025-46149
5.3
EPSS 0.4%
DoSData LeakageSupply ChainFrameworkInference
pytorch26.1K4 ATLAS
MEDIUM

PyTorch: PairwiseDistance silent miscalculation, integrity risk

CVE-2025-46148
5.3
EPSS 0.4%
Adversarial ExamplesAuth BypassFrameworkInference
pytorch26.1K4 ATLAS
MEDIUM

n8n: stored XSS in LangChain chat trigger (public)

CVE-2025-58177
5.4
EPSS 0.2%
Social EngineeringData ExtractionFrameworkAgent
n8n165 ATLAS
MEDIUMEXPLOIT AVAIL

Transformers: ReDoS in EnglishNormalizer exhausts CPU

CVE-2025-6051
5.3
EPSS 0.4%
DoSFrameworkInference
transformersCWE-13339.8K4 ATLAS
MEDIUMEXPLOIT AVAIL

xgrammar: DoS via oversized JSON schema grammar parsing

CVE-2025-58446
--
EPSS 0.6%
DoSInferenceFramework
xgrammarPatch: 0.1.24CWE-7701323 ATLAS
MEDIUM

picklescan: scanner bypass enables model RCE

GHSA-q77w-mwjj-7mqx
--
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 0.0.3036 ATLAS
MEDIUM

picklescan: scanner bypass enables RCE via ML model files

GHSA-49gj-c84q-6qm9
--
Supply ChainCode ExecutionModelFramework
picklescanPatch: 0.0.3035 ATLAS
MEDIUM

picklescan: scan bypass allows silent RCE via ML models

GHSA-9w88-8rmg-7g2p
--
Supply ChainCode ExecutionModelFramework
picklescanPatch: 0.0.3036 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