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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 1245 results — has patch
MEDIUM

picklescan: PyTorch gadget bypasses pickle RCE detection

GHSA-vr7h-p6mm-wpmh
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.28 CWE-345 3 5 ATLAS
MEDIUM

picklescan: detection bypass via PyTorch proxy RCE

GHSA-h3qp-7fh3-f8h4
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.28 3 7 ATLAS
MEDIUM

picklescan: RCE bypass via torch.utils.collect_env

GHSA-f745-w6jp-hpxx
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.28 CWE-345 3 5 ATLAS
MEDIUM

picklescan: scanner bypass enables RCE via PyTorch function

GHSA-f4x7-rfwp-v3xw
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.28 CWE-345 3 5 ATLAS
MEDIUM

picklescan: detection bypass enables PyTorch model RCE

GHSA-86cj-95qr-2p4f
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.28 CWE-345 3 6 ATLAS
MEDIUM

picklescan: PyTorch bypass allows undetected RCE

GHSA-4r9r-ch6f-vxmx
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.28 CWE-345 3 5 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 92 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-502 765 5 ATLAS
CRITICAL

ExecuTorch: integer overflow RCE on model load

CVE-2025-30404
9.8
EPSS 0.6%
Code Execution Supply Chain Framework Model Inference
executorch Patch: 0.7.0 CWE-190 6 5 ATLAS
CRITICAL EXPLOIT AVAIL

ExecuTorch: OOB read in model loader enables RCE

CVE-2025-54950
9.8
EPSS 0.6%
Code Execution Supply Chain Framework Model Inference
executorch Patch: 0.7.0 CWE-125 6 4 ATLAS
CRITICAL

ExecuTorch: heap buffer overflow RCE in model loading

CVE-2025-54951
9.8
EPSS 0.7%
Code Execution Supply Chain Framework Model Inference
executorch Patch: 0.7.0 CWE-122 6 4 ATLAS
CRITICAL

ExecuTorch: integer overflow in model load → RCE

CVE-2025-30405
9.8
EPSS 0.6%
Code Execution Supply Chain Framework Model Inference
executorch Patch: 0.7.0 CWE-190 6 4 ATLAS
CRITICAL

ExecuTorch: heap buffer overflow RCE via model loading

CVE-2025-54949
9.8
EPSS 0.7%
Code Execution Supply Chain Framework Model
executorch Patch: 0.7.0 CWE-122 6 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-351 765 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-351 765 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 6 3 ATLAS
MEDIUM EXPLOIT AVAIL

llama-index: DocugamiReader MD5 hash collision drops chunks

CVE-2025-6211
6.5
EPSS 0.3%
Supply Chain Data Leakage Framework RAG
llama-index-readers-docugami Patch: 0.3.1 CWE-440 249 4 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
MEDIUM EXPLOIT AVAIL

llama-index: JSONReader DoS via recursive JSON parsing

CVE-2025-5472
6.5
EPSS 0.3%
DoS Framework
llama-index-core Patch: 0.12.38 CWE-674 1.2K 3 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