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
3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 1076 results — has patch
MEDIUM

langgraph: Deserialization enables RCE

CVE-2026-28277
6.8
EPSS 4.9%
Code Execution Data Leakage Supply Chain Framework Agent
langgraph Patch: 1.0.10 CWE-502 3.7K 5 ATLAS
HIGH EXPLOIT AVAIL

xgrammar: security flaw enables exploitation

CVE-2026-25048
7.5
EPSS 0.7%
DoS Inference Framework
xgrammar Patch: 0.1.32 CWE-674 16 4 ATLAS
HIGH

fickling: Allowlist Bypass evades input filtering

GHSA-5hwf-rc88-82xm
--
Supply Chain Code Execution Framework Model
fickling Patch: 0.1.9 CWE-184 61 5 ATLAS
HIGH

fickling: Protection Bypass circumvents security controls

GHSA-wccx-j62j-r448
--
Code Execution Supply Chain Auth Bypass Framework Model Inference
fickling Patch: 0.1.9 CWE-693 61 5 ATLAS
CRITICAL

picklescan: Allowlist Bypass evades input filtering

GHSA-g38g-8gr9-h9xp
9.8
Supply Chain Code Execution Framework Model
picklescan Patch: 1.0.4 CWE-184 3 7 ATLAS 1 incident
CRITICAL

picklescan: security flaw enables exploitation

GHSA-vvpj-8cmc-gx39
10.0
Supply Chain Code Execution Auth Bypass Model Framework
picklescan Patch: 1.0.4 CWE-183 3 8 ATLAS
CRITICAL

picklescan: Allowlist Bypass evades input filtering

GHSA-7wx9-6375-f5wh
9.8
Supply Chain Code Execution Framework
picklescan Patch: 1.0.4 CWE-184 3 5 ATLAS
MEDIUM

langgraph-checkpoint: Deserialization enables RCE

CVE-2026-27794
6.6
EPSS 0.7%
Code Execution Supply Chain Framework Agent
langgraph-checkpoint Patch: 4.0.0 CWE-502 3.7K 4 ATLAS
MEDIUM

fickling: Allowlist Bypass evades input filtering

GHSA-mhc9-48gj-9gp3
--
Supply Chain Code Execution Framework Model
fickling Patch: 0.1.8 CWE-184 61 7 ATLAS
HIGH

fickling: security flaw enables exploitation

GHSA-mxhj-88fx-4pcv
--
Supply Chain Code Execution Auth Bypass Framework Model
fickling Patch: 0.1.8 CWE-436 61 6 ATLAS
CRITICAL

mlflow: security flaw enables exploitation

CVE-2026-2635
9.8
EPSS 1.0%
Model Poisoning Code Execution Auth Bypass Framework RAG Model
mlflow Patch: 3.8.0rc0 CWE-1393 674 10 ATLAS
HIGH

mlflow: Path Traversal enables file access

CVE-2026-2033
8.1
EPSS 1.7%
Data Extraction Model Poisoning Code Execution Framework RAG Model
mlflow Patch: 3.8.0rc0 CWE-22 674 11 ATLAS
HIGH EXPLOIT AVAIL

google-cloud-aiplatform: XSS enables session hijacking

CVE-2026-2472
8.1
EPSS 0.5%
Code Execution Data Extraction Supply Chain Framework API
google-cloud-aiplatform Patch: 1.131.0 CWE-79 201 8 ATLAS
MEDIUM EXPLOIT AVAIL

ray: Missing Auth allows unauthenticated access

CVE-2026-27482
5.9
EPSS 0.3%
Auth Bypass DoS Framework Inference
ray Patch: 2.54.0 CWE-306 619 4 ATLAS
LOW

fickling: Allowlist Bypass evades input filtering

GHSA-83pf-v6qq-pwmr
--
Supply Chain Code Execution Data Extraction Framework Model Training Data
fickling Patch: 0.1.8 CWE-184 61 6 ATLAS
CRITICAL

semantic-kernel: Code Injection enables RCE

CVE-2026-26030
10.0
EPSS 3.7%
Code Execution Supply Chain Auth Bypass Framework Agent RAG
semantic-kernel Patch: 1.39.4 CWE-94 31 5 ATLAS
HIGH

picklescan: Allowlist Bypass evades input filtering

GHSA-97f8-7cmv-76j2
--
Code Execution Supply Chain Model Framework
picklescan Patch: 1.0.3 CWE-184 3 7 ATLAS
CRITICAL

semantic-kernel: Path Traversal enables file access

CVE-2026-25592
9.9
EPSS 2.4%
Code Execution Supply Chain Data Extraction Framework Agent Plugin
semantic-kernel Patch: 1.39.3 CWE-22 31 6 ATLAS
HIGH EXPLOIT AVAIL

pydantic-ai: SSRF allows internal network access

CVE-2026-25580
8.6
EPSS 0.6%
Data Extraction Auth Bypass Framework Agent API
pydantic-ai-slim Patch: 1.56.0 CWE-918 483 6 ATLAS
MEDIUM

pydantic-ai: Path Traversal enables file access

CVE-2026-25640
5.4
EPSS 0.3%
Code Execution Data Extraction Framework Agent
pydantic-ai-slim Patch: 1.51.0 CWE-22 483 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