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
2,388

AI/ML CVEs Tracked

342

Critical

358

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 2388 results
CRITICAL EXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model loading

CVE-2025-1550
9.8
EPSS 2.8%
Code Execution Supply Chain Framework Model
keras CWE-94 1.6K 6 ATLAS
LOW EXPLOIT AVAIL

PyTorch: improper init in quantized sigmoid skews model output

CVE-2025-2149
2.5
EPSS 0.2%
Supply Chain Adversarial Examples Framework Inference Model
torch CWE-665 22.7K 3 ATLAS
HIGH EXPLOIT AVAIL

PyTorch: memory corruption in JIT profiler callback handler

CVE-2025-2148
7.5
EPSS 0.4%
Code Execution Supply Chain Framework Inference
torch CWE-119 22.7K 3 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: ZIP flag bypass enables RCE in PyTorch models

CVE-2025-1945
9.8
EPSS 0.5%
Supply Chain Code Execution Model Framework
picklescan CWE-345 3 6 ATLAS
MEDIUM EXPLOIT AVAIL

picklescan: ZIP spoof lets malicious PyTorch models bypass scan

CVE-2025-1944
6.5
EPSS 0.3%
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.23 CWE-345 3 5 ATLAS
MEDIUM

Ray: Redis password exposed via plaintext logging

CVE-2025-1979
6.4
EPSS 0.2%
Data Leakage Data Extraction Framework Training Data
ray Patch: 2.43.0 CWE-532 873 4 ATLAS
CRITICAL EXPLOIT AVAIL

spacy-llm: SSTI allows unauthenticated RCE (CVSS 9.8)

CVE-2025-25362
9.8
EPSS 0.7%
Code Execution Data Extraction Framework
spacy-llm Patch: 0.7.3 CWE-94 143 4 ATLAS
CRITICAL

B2B Login Panel: SQLi enables unauthenticated DB access

CVE-2024-13147
9.8
EPSS 0.4%
Auth Bypass Data Extraction Framework API
B2B Login Panel 479 4 ATLAS
LOW

vLLM AIBrix: weak hash in prefix cache leaks inference patterns

CVE-2025-1953
2.6
EPSS 0.3%
Data Leakage Privacy Violation Inference Framework
3 ATLAS
MEDIUM EXPLOIT AVAIL

picklescan: scanner bypass enables supply chain RCE

CVE-2025-1716
--
EPSS 1.5%
Supply Chain Code Execution Model Framework
picklescan Patch: 0.0.22 CWE-184 3 5 ATLAS
MEDIUM EXPLOIT AVAIL

picklescan: extension bypass enables RCE on model load

CVE-2025-1889
--
EPSS 0.4%
Supply Chain Code Execution Model Framework
picklescan Patch: 0.0.22 CWE-646 3 5 ATLAS
HIGH EXPLOIT AVAIL

gpt_academic: symlink traversal exposes all server files

CVE-2025-25185
7.5
EPSS 0.6%
Data Extraction Privacy Violation Framework
gpt_academic 4 ATLAS
CRITICAL

JupyterHub LTI13: JWT forgery enables full auth bypass

CVE-2023-25574
10.0
EPSS 0.3%
Auth Bypass Framework
jupyterhub-ltiauthenticator Patch: 1.4.0 CWE-347 1.9K 3 ATLAS
HIGH

Label Studio: SSRF via S3 endpoint exposes internal services

CVE-2025-25297
8.6
EPSS 0.5%
Data Extraction Auth Bypass Framework Training Data
label-studio Patch: 1.16.0 CWE-918 1 4 ATLAS
MEDIUM EXPLOIT AVAIL SCANNER

Label Studio: reflected XSS via label_config param

CVE-2025-25296
6.1
EPSS 1.8%
Code Execution Data Extraction Training Data Framework
label-studio Patch: 1.16.0 CWE-79 1 4 ATLAS
HIGH EXPLOIT AVAIL

Label Studio SDK: path traversal leaks server filesystem

CVE-2025-25295
--
EPSS 0.7%
Data Extraction Data Leakage Privacy Violation Framework Training Data
label-studio-sdk Patch: 1.0.10 CWE-26 1 5 ATLAS
CRITICAL

Mobuy Panel: SQLi allows unauthenticated DB takeover

CVE-2024-13152
10.0
EPSS 0.5%
Data Extraction Auth Bypass Code Execution Framework
Mobuy Online Machinery Monitoring Panel 479 4 ATLAS
CRITICAL

PandasAI: prompt injection enables unauthenticated RCE

CVE-2024-12366
9.8
EPSS 1.2%
Prompt Injection Code Execution Framework Agent
CWE-94 6 ATLAS
MEDIUM

serialize-javascript: XSS via regex in AI/ML dashboards

CVE-2024-11831
5.4
EPSS 1.0%
Supply Chain Code Execution Data Extraction Framework Plugin
odh-kf-notebook-controller-rhel8 3.0K 4 ATLAS
LOW

vLLM: hash collision enables prefix cache poisoning

CVE-2025-25183
2.6
EPSS 0.2%
Adversarial Examples Data Leakage Inference Framework
vllm CWE-354 130 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