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 1431 results — has patch
HIGH

picklescan: Code Injection enables RCE

GHSA-3329-ghmp-jmv5
--
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 0.0.33CWE-9435 ATLAS
HIGH

picklescan: Code Injection enables RCE

GHSA-x843-g5mx-g377
--
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 0.0.33CWE-9436 ATLAS
HIGH

picklescan: Deserialization enables RCE

GHSA-r8g5-cgf2-4m4m
--
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 0.0.33CWE-50235 ATLAS
HIGH

picklescan: Protection Bypass circumvents security controls

GHSA-hgrh-qx5j-jfwx
8.8
Supply ChainCode ExecutionModelFramework
picklescanPatch: 0.0.33CWE-69337 ATLAS
HIGH

picklescan: Deserialization enables RCE

GHSA-vqmv-47xg-9wpr
--
Supply ChainCode ExecutionModelFramework
picklescanPatch: 0.0.33CWE-50237 ATLAS
HIGH

picklescan: Allowlist Bypass evades input filtering

GHSA-84r2-jw7c-4r5q
--
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 0.0.33CWE-18435 ATLAS
HIGH

picklescan: Allowlist Bypass evades input filtering

GHSA-4675-36f9-wf6r
--
Code ExecutionSupply ChainAuth BypassFrameworkModel
picklescanPatch: 0.0.33CWE-18436 ATLAS
HIGH

picklescan: Deserialization enables RCE

GHSA-m273-6v24-x4m4
--
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 0.0.33CWE-50235 ATLAS
HIGHEXPLOIT AVAIL

lmdeploy: Deserialization enables RCE

CVE-2025-67729
8.8
EPSS 0.5%
Supply ChainCode ExecutionFrameworkModelInference
lmdeployPatch: 0.11.1CWE-50216 ATLAS
MEDIUMEXPLOIT AVAIL

local-deep-research: SSRF allows internal network access

CVE-2025-67743
6.3
EPSS 0.3%
Data ExtractionAuth BypassFrameworkAPI
local-deep-researchPatch: 1.3.9CWE-9184 ATLAS
HIGHEXPLOIT AVAIL

fickling: Code Injection enables RCE

CVE-2025-67748
--
EPSS 0.3%
Supply ChainCode ExecutionFrameworkModel
ficklingPatch: 0.1.6CWE-94625 ATLAS
HIGHEXPLOIT AVAIL

fickling: Allowlist Bypass evades input filtering

CVE-2025-67747
--
EPSS 0.3%
Supply ChainCode ExecutionFrameworkModel
ficklingPatch: 0.1.6CWE-184625 ATLAS
HIGH

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-67644
7.3
EPSS 2.3%
Auth BypassData ExtractionFrameworkAgent
langgraph-checkpoint-sqlitePatch: 3.0.1CWE-894.1K4 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF allows internal network access

CVE-2025-65958
8.5
EPSS 4.7%
Data ExtractionData LeakageCode ExecutionAPIRAG
open-webuiPatch: 0.6.37CWE-91826 ATLAS
CRITICALKEVSCANNER

ray: Code Injection enables RCE

CVE-2025-62593
--
EPSS 60.2%
Code ExecutionAuth BypassSocial EngineeringFramework
rayPatch: 2.52.0CWE-946428 ATLAS
HIGH

langchain-core: security flaw enables exploitation

CVE-2025-65106
--
EPSS 0.5%
Prompt InjectionCode ExecutionData ExtractionFrameworkAgent
langchain-corePatch: 1.0.7CWE-13366.3K7 ATLAS
HIGHEXPLOIT AVAIL

open-webui: Code Injection enables RCE

CVE-2025-64496
7.3
EPSS 7.2%
Code ExecutionAuth BypassSocial EngineeringInferenceAPIPlugin
open-webuiPatch: 0.6.35CWE-9529 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: XSS-to-RCE via malicious prompt injection

CVE-2025-64495
8.7
EPSS 0.5%
Code ExecutionData ExtractionAuth BypassFrameworkAgentAPI
open-webuiPatch: 0.6.35CWE-7927 ATLAS
HIGHEXPLOIT AVAIL

langgraph-checkpoint: Deserialization enables RCE

CVE-2025-64439
--
EPSS 0.9%
Code ExecutionSupply ChainFrameworkAgent
langgraph-checkpointPatch: 3.0.0CWE-5024.1K5 ATLAS
CRITICALEXPLOIT AVAIL

keras: Path Traversal enables file access

CVE-2025-12060
9.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkTraining Data
kerasPatch: 3.12.0CWE-224.1K4 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