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
2,377

AI/ML CVEs Tracked

337

Critical

392

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 509 results — High severity, Active exploitation
HIGH EXPLOIT AVAIL

ollama: Input Validation flaw enables exploitation

CVE-2025-66960
7.5
EPSS 0.4%
DoS Inference Framework Model
ollama 1.6K 5 ATLAS
HIGH EXPLOIT AVAIL

ollama: Input Validation flaw enables exploitation

CVE-2025-66959
7.5
EPSS 4.5%
DoS Inference Framework
ollama 1.6K 3 ATLAS
HIGH EXPLOIT AVAIL

chainlit: SSRF allows internal network access

CVE-2026-22219
7.7
EPSS 4.4%
Data Extraction Privacy Violation Framework API
chainlit Patch: 2.9.4 CWE-918 40 5 ATLAS
HIGH EXPLOIT AVAIL

ollama: security flaw enables exploitation

CVE-2025-15514
7.5
EPSS 0.6%
DoS Inference API Framework
ollama CWE-395 1.6K 4 ATLAS
HIGH EXPLOIT AVAIL

langchain: security flaw enables exploitation

CVE-2024-58340
7.5
EPSS 0.4%
DoS Prompt Injection Framework Agent
langchain CWE-1333 2.7K 8 ATLAS
HIGH EXPLOIT AVAIL

llamaindex: Resource Exhaustion enables DoS

CVE-2024-58339
7.5
EPSS 0.6%
DoS Code Execution Framework Agent
llamaindex CWE-770 5 ATLAS
HIGH EXPLOIT AVAIL

llamaindex: Deserialization enables RCE

CVE-2024-14021
7.8
EPSS 0.3%
Code Execution Supply Chain Framework RAG
llamaindex CWE-502 6 ATLAS
HIGH EXPLOIT AVAIL

label-studio: XSS enables session hijacking

CVE-2026-22033
--
EPSS 0.2%
Auth Bypass Data Extraction Supply Chain Training Data Framework API
label-studio CWE-79 1 7 ATLAS
HIGH EXPLOIT AVAIL

vllm: Resource Exhaustion enables DoS

CVE-2026-22773
7.5
EPSS 0.4%
DoS Inference Framework
vllm CWE-770 130 4 ATLAS
HIGH EXPLOIT AVAIL

fickling: Deserialization enables RCE

CVE-2026-22612
--
EPSS 0.3%
Supply Chain Code Execution Auth Bypass Framework Model Training Data
fickling Patch: 0.1.7 CWE-502 58 5 ATLAS
HIGH EXPLOIT AVAIL

fickling: Allowlist Bypass evades input filtering

CVE-2026-22609
--
EPSS 0.6%
Code Execution Supply Chain Auth Bypass Framework Model
fickling Patch: 0.1.7 CWE-184 58 5 ATLAS
HIGH EXPLOIT AVAIL

fickling: Allowlist Bypass evades input filtering

CVE-2026-22608
--
EPSS 0.3%
Supply Chain Code Execution Auth Bypass Framework Model
fickling Patch: 0.1.7 CWE-184 58 5 ATLAS
HIGH EXPLOIT AVAIL

fickling: Allowlist Bypass evades input filtering

CVE-2026-22607
--
EPSS 0.4%
Code Execution Supply Chain Auth Bypass Framework Model Inference
fickling Patch: 0.1.7 CWE-184 58 6 ATLAS
HIGH EXPLOIT AVAIL

fickling: Allowlist Bypass evades input filtering

CVE-2026-22606
--
EPSS 0.4%
Supply Chain Code Execution Framework Model
fickling Patch: 0.1.7 CWE-184 58 5 ATLAS
HIGH EXPLOIT AVAIL

OAI CN5G AMF: unauthenticated JSON DoS on 5G SBI interface

CVE-2025-66786
7.5
EPSS 0.3%
DoS API Inference
oai-cn5g-amf 16.6K 3 ATLAS
HIGH EXPLOIT AVAIL

OAI CN5G AMF: Unauthenticated buffer overflow, RCE/DoS

CVE-2025-65805
7.5
EPSS 0.3%
DoS Code Execution Inference API
oai-cn5g-amf 16.6K 3 ATLAS
HIGH EXPLOIT AVAIL

mcp_typescript_sdk: security flaw enables exploitation

CVE-2026-0621
7.5
EPSS 0.4%
DoS Framework API Agent
4 ATLAS
HIGH EXPLOIT AVAIL

lmdeploy: Deserialization enables RCE

CVE-2025-67729
8.8
EPSS 0.5%
Supply Chain Code Execution Framework Model Inference
lmdeploy Patch: 0.11.1 CWE-502 1 6 ATLAS
HIGH EXPLOIT AVAIL

langchain-core: Deserialization enables RCE

CVE-2025-68664
8.2
EPSS 13.8%
Supply Chain Code Execution Data Extraction Framework Agent
langchain_core CWE-502 2.7K 6 ATLAS
HIGH KEV SCANNER

n8n: security flaw enables exploitation

CVE-2025-68613
8.8
EPSS 97.9%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-913 9 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