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 1164 results — Active exploitation, no patch
MEDIUM EXPLOIT AVAIL

PraisonAI: sandbox bypass leaks agent internals

CVE-2026-57120
6.5
EPSS 0.3%
Data Extraction Prompt Injection Code Execution Agent Framework
praisonaiagents CWE-693 20 4 ATLAS
LOW EXPLOIT AVAIL

vLLM: local DoS via malformed tiktoken vocab file

CVE-2026-90713
3.3
EPSS 0.2%
DoS Supply Chain Inference Model
vllm CWE-404 92 2 ATLAS
HIGH EXPLOIT AVAIL

CrewAI before fb2323b offers a Python blocklist approach that operates at the wrong level of abstraction, a different vulnerability than CVE-2026-2275....

CVE-2026-37008
8.1
EPSS 0.1%
CWE-424
MEDIUM EXPLOIT AVAIL

Flowise: SSRF via Host/X-Forwarded-Proto in Evaluations

CVE-2026-90580
6.3
EPSS 0.2%
Data Extraction Privacy Violation Agent API
flowise CWE-918 2 ATLAS
HIGH EXPLOIT AVAIL

ESPnet: RCE via unsafe checkpoint deserialization

CVE-2026-90777
8.8
EPSS 0.5%
Supply Chain Code Execution Model Training Data Framework
CWE-502 3 ATLAS
HIGH EXPLOIT AVAIL

Open Notebook: SSRF via source URL hits internal services

CVE-2026-90769
7.7
EPSS 0.3%
Data Leakage Privacy Violation RAG Framework
CWE-918 2 ATLAS
HIGH EXPLOIT AVAIL

Flowise: IDOR in abort API enables agent DoS

CVE-2026-90535
7.5
EPSS 0.3%
Auth Bypass DoS Agent API
flowise CWE-862 2 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: IDOR exposes org owner's password hash

CVE-2026-90533
6.5
EPSS 0.2%
Auth Bypass Data Leakage Agent Framework
flowise CWE-862 3 ATLAS
MEDIUM EXPLOIT AVAIL

WPBot: unauthenticated AJAX abuse drains AI API budget

CVE-2026-87918
5.3
EPSS 0.2%
Auth Bypass DoS Plugin API
WPBot 4 ATLAS
MEDIUM EXPLOIT AVAIL

WPBot: missing auth check leaks chat visitor PII

CVE-2026-87916
5.3
EPSS 0.2%
Auth Bypass Privacy Violation Data Leakage Agent Plugin
WPBot 2 ATLAS
CRITICAL EXPLOIT AVAIL

Mistral Vibe: env-var trick bypasses command allowlist

CVE-2026-87987
--
EPSS 0.3%
Code Execution Auth Bypass Agent Framework
mistral-vibe 492 5 ATLAS
HIGH EXPLOIT AVAIL

Headroom: CSWSH bypass allows unauthenticated LLM abuse

CVE-2026-71416
8.8
EPSS 0.2%
Auth Bypass Data Leakage API Inference
3 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: stored XSS in notebook template paths

CVE-2026-87811
7.3
EPSS 0.2%
Code Execution Data Leakage Plugin
1 ATLAS
AWAITING NVD EXPLOIT AVAIL

MLflow: malicious model artifact enables RCE on load

CVE-2026-79721
--
EPSS 0.3%
Supply Chain Code Execution Framework Model
mlflow 690 4 ATLAS
MEDIUM EXPLOIT AVAIL

Ollama: integer overflow in GGUF decoder causes DoS

CVE-2026-86289
4.3
EPSS 0.4%
DoS Supply Chain Inference Model
ollama CWE-189 1.8K 3 ATLAS
HIGH EXPLOIT AVAIL

Pterodactyl Panel: subuser escalation to console RCE

CVE-2026-86177
8.8
EPSS 0.3%
Auth Bypass Code Execution Framework
CWE-862
HIGH EXPLOIT AVAIL

LLaMA-Factory: SSRF guard bypass via redirect/DNS rebind

CVE-2026-85673
7.5
EPSS 0.4%
Auth Bypass Data Extraction API Inference
llama-factory CWE-918 3 ATLAS
MEDIUM EXPLOIT AVAIL

tokenizers: malformed vocab crashes process (DoS)

CVE-2026-85670
6.5
EPSS 0.3%
DoS Supply Chain Inference Training Data
tokenizers CWE-787 15.9K 3 ATLAS
HIGH EXPLOIT AVAIL

OGX/Llama Stack: SSRF via MCP tool server_url

CVE-2026-85666
7.5
EPSS 0.4%
Data Leakage Auth Bypass Agent API Plugin
llama-stack CWE-918 13 3 ATLAS
UNKNOWN EXPLOIT AVAIL

csv-parse: CSV header triggers prototype pollution

CVE-2026-85063
--
EPSS 0.3%
Supply Chain Auth Bypass Training Data RAG
CWE-1321 2 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