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.

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

Latest AI Security Threats

Showing 20 of 108 results — Critical severity, has patch
CRITICAL EXPLOIT AVAIL

PraisonAI: RCE via shell injection in memory hooks executor

CVE-2026-40111
--
EPSS 0.2%
Code Execution Prompt Injection Agent Framework
praisonaiagents Patch: 1.5.128 CWE-78 11 5 ATLAS
CRITICAL

PraisonAI: RCE via shell injection in agent workflows

GHSA-2763-cj5r-c79m
9.7
Code Execution Prompt Injection Supply Chain Agent Framework
PraisonAI Patch: 4.5.121 CWE-78 1 6 ATLAS
CRITICAL

Marimo: pre-auth RCE via terminal WebSocket

GHSA-2679-6mx9-h9xc
--
Auth Bypass Code Execution Framework
marimo Patch: 0.23.0 CWE-306 3.0K 5 ATLAS
CRITICAL

praisonaiagents: sandbox escape enables host RCE

CVE-2026-39888
10.0
EPSS 0.5%
Code Execution Auth Bypass Agent Framework
praisonaiagents Patch: 1.5.115 CWE-657 11 5 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: YAML deserialization enables unauthenticated RCE

CVE-2026-39890
9.8
EPSS 0.6%
Code Execution Supply Chain Agent Framework
praisonai Patch: 4.5.115 CWE-502 1 5 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: path traversal exposes full filesystem via agent tools

CVE-2026-35615
--
EPSS 0.4%
Data Extraction Code Execution Agent Framework
PraisonAI Patch: 1.5.113 CWE-22 1 5 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: path traversal enables arbitrary file write/RCE

CVE-2026-39305
9.0
EPSS 0.3%
Code Execution Prompt Injection Supply Chain Agent Framework
PraisonAI Patch: 4.5.113 1 5 ATLAS
CRITICAL

LiteLLM: auth bypass via JWT cache key collision

CVE-2026-35030
9.1
EPSS 0.4%
Auth Bypass Data Extraction API Framework Inference
litellm Patch: 1.83.0 CWE-287 6 4 ATLAS
CRITICAL EXPLOIT AVAIL

praisonaiagents: sandbox bypass enables full host RCE

CVE-2026-34938
10.0
EPSS 0.7%
Code Execution Prompt Injection Supply Chain Agent Framework Plugin
praisonaiagents Patch: 1.5.90 CWE-693 11 7 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: command injection via model_uri in mlserver mode

CVE-2026-0596
9.6
EPSS 1.3%
Code Execution Supply Chain Framework Inference
mlflow Patch: 3.9.0 CWE-78 655 4 ATLAS 1 incident
CRITICAL EXPLOIT AVAIL

MLflow: RCE via unsanitized model dependency specs

CVE-2025-15379
10.0
EPSS 2.4%
Code Execution Supply Chain Framework
mlflow Patch: 3.8.1 CWE-77 655 4 ATLAS 1 incident
CRITICAL EXPLOIT AVAIL

MLflow: path traversal enables sandbox escape, file overwrite

CVE-2025-15036
9.6
EPSS 0.5%
Supply Chain Code Execution Framework
mlflow Patch: 3.9.0rc0 CWE-29 655 5 ATLAS
CRITICAL

n8n: stored XSS enables credential theft via workflow

CVE-2026-33749
9.0
EPSS 0.2%
Data Extraction Auth Bypass Code Execution Agent Framework API
n8n Patch: 1.123.27 CWE-79 8 ATLAS
CRITICAL

n8n: member role steals plaintext HTTP credentials

CVE-2026-33663
10.0
EPSS 0.4%
Auth Bypass Data Extraction Data Leakage Agent Framework API
n8n Patch: 1.123.27 CWE-639 6 ATLAS
CRITICAL

TensorFlow: type confusion NPD in tensor conversion

CVE-2026-33660
10.0
EPSS 1.0%
Code Execution DoS Framework Inference
n8n Patch: 2.14.1 CWE-94 3 ATLAS
CRITICAL EXPLOIT AVAIL

langflow: Path Traversal enables file access

CVE-2026-33309
9.9
EPSS 1.4%
Code Execution Auth Bypass Supply Chain Framework Agent Plugin
langflow Patch: 1.9.0 CWE-22 8 ATLAS
CRITICAL KEV SCANNER

langflow: Code Injection enables RCE

CVE-2026-33017
9.8
EPSS 98.4%
Model Poisoning Code Execution Framework Agent API
langflow Patch: 1.9.0 CWE-95 6 ATLAS
CRITICAL EXPLOIT AVAIL

mlflow: Path Traversal enables file access

CVE-2025-15031
9.1
EPSS 0.7%
Supply Chain Model Poisoning Code Execution Framework Model Training Data
mlflow Patch: 3.9.0rc0 CWE-22 655 6 ATLAS
CRITICAL EXPLOIT AVAIL

mcp-atlassian: Path Traversal enables file access

CVE-2026-27825
9.1
EPSS 2.3%
Code Execution Prompt Injection Supply Chain Agent Plugin Framework
mcp-atlassian Patch: 0.17.0 CWE-22 6 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

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