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
2,387

AI/ML CVEs Tracked

341

Critical

365

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 352 results — High severity, has patch
HIGH EXPLOIT AVAIL SCANNER

EverNoteLoader: XXE exposes host files in LangChain

CVE-2025-6984
7.5
EPSS 1.5%
Data Extraction Data Leakage Framework RAG
langchain-community Patch: 0.3.27 CWE-200 1.2K 4 ATLAS
HIGH EXPLOIT AVAIL

llama-index: JSON parsing DoS via deep recursion

CVE-2025-5302
8.6
EPSS 0.3%
DoS Framework RAG
llama-index-core Patch: 0.12.38 CWE-674 1.2K 3 ATLAS
HIGH EXPLOIT AVAIL

xgrammar: uncontrolled recursion in grammar parsing causes DoS

CVE-2025-57809
7.5
EPSS 0.4%
DoS Supply Chain Framework Inference
xgrammar Patch: 0.1.21 CWE-674 160 3 ATLAS
HIGH

vLLM: RCE via eval() in Qwen3 Coder tool parser

CVE-2025-9141
8.8
EPSS 4.0%
Code Execution Supply Chain Inference Framework Agent
vllm Patch: 0.10.1.1 CWE-502 130 5 ATLAS
HIGH

picklescan: detection bypass allows malicious pickle exec

GHSA-9gvj-pp9x-gcfr
--
Supply Chain Code Execution Auth Bypass Framework Model
picklescan Patch: 0.0.27 CWE-502 3 6 ATLAS
HIGH EXPLOIT AVAIL

skops: joblib fallback enables RCE via model load

CVE-2025-54886
8.4
EPSS 0.2%
Supply Chain Code Execution Framework Model
skops Patch: 0.13.0 CWE-502 711 5 ATLAS
HIGH EXPLOIT AVAIL

skops: RCE via MethodNode unsafe deserialization

CVE-2025-54413
--
EPSS 0.1%
Code Execution Supply Chain Framework Model
skops Patch: 0.12.0 CWE-351 711 4 ATLAS
HIGH EXPLOIT AVAIL

skops: OperatorFuncNode type confusion → RCE

CVE-2025-54412
--
EPSS 0.1%
Supply Chain Code Execution Framework Model
skops Patch: 0.12.0 CWE-351 711 4 ATLAS
HIGH

ExecuTorch: heap overflow in method load, RCE risk

CVE-2025-30402
8.1
EPSS 0.4%
Code Execution Supply Chain Framework Inference Model
executorch Patch: 0.7.0-rc1 CWE-122 1 3 ATLAS
HIGH EXPLOIT AVAIL

llama_index: path traversal allows arbitrary file read

CVE-2025-6209
7.5
EPSS 0.5%
Data Extraction Data Leakage Framework RAG
llama-index-core Patch: 0.12.41 CWE-29 1.2K 4 ATLAS
HIGH EXPLOIT AVAIL

LlamaIndex Obsidian: symlink traversal exposes host files

CVE-2025-3046
7.5
EPSS 0.6%
Data Extraction Data Leakage Framework RAG
llama-index-readers-obsidian Patch: 0.5.1 CWE-22 238 4 ATLAS
HIGH EXPLOIT AVAIL

llama-index Papers Loader: XML expansion DoS

CVE-2025-3225
7.5
EPSS 0.4%
DoS Supply Chain Framework RAG
llama-index-readers-papers Patch: 0.3.2 CWE-776 238 3 ATLAS
HIGH EXPLOIT AVAIL

jupyter_core: config hijack enables cross-user code exec

CVE-2025-30167
7.3
EPSS 0.2%
Code Execution Supply Chain Data Extraction Framework Training Data
jupyter_core Patch: 5.8.1 CWE-427 1.9K 4 ATLAS
HIGH EXPLOIT AVAIL

Label Studio: XSS enables unauthorized actions via CSRF

CVE-2025-47783
--
EPSS 0.5%
Code Execution Data Leakage Social Engineering Framework Training Data
label-studio Patch: 1.18.0 CWE-79 1 5 ATLAS
HIGH EXPLOIT AVAIL

llama_index: DoS via uncapped recursion in web reader

CVE-2025-1752
7.5
EPSS 0.4%
DoS Framework RAG
llama-index Patch: 0.12.21 CWE-400 238 3 ATLAS
HIGH EXPLOIT AVAIL

LLaMA-Factory: RCE via torch.load() unsafe deserialization

CVE-2025-46567
7.8
EPSS 0.2%
Code Execution Supply Chain Framework Training Data
llamafactory Patch: 0.9.3 CWE-502 1 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables DNS data exfiltration

CVE-2025-46417
--
EPSS 0.2%
Supply Chain Data Extraction Data Leakage Framework Model
picklescan Patch: 0.0.25 CWE-184 3 6 ATLAS
HIGH EXPLOIT AVAIL

jupyterlab-git: command injection via malicious repo name

CVE-2025-30370
7.4
EPSS 0.5%
Code Execution Supply Chain Framework Plugin
jupyterlab-git Patch: 0.51.1 CWE-78 1.9K 4 ATLAS
HIGH EXPLOIT AVAIL

litellm: privilege escalation viewer→proxy admin via bad API key

CVE-2025-0628
8.1
EPSS 0.3%
Auth Bypass Data Extraction API Framework
litellm Patch: 1.61.15 CWE-266 6 4 ATLAS
HIGH

LiteLLM: API key leakage in logs exposes credentials

CVE-2024-9606
7.5
EPSS 0.7%
Data Leakage Data Extraction Auth Bypass Framework API Agent
litellm Patch: 1.44.12 CWE-117 6 5 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