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
3,591

AI/ML CVEs Tracked

481

Critical

84

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 2346 results — no patch
HIGH

OpenClaw: symlink following bypasses authorization

CVE-2026-62189
7.1
EPSS 0.4%
Auth Bypass Agent Plugin
openclaw CWE-59 3 3 ATLAS
HIGH

OpenClaw Feishu: authz bypass ignores disablement

CVE-2026-62188
8.1
EPSS 0.4%
Auth Bypass Data Leakage Agent Plugin
openclaw\/feishu CWE-863 3 3 ATLAS
HIGH

OpenClaw Feishu: disabled accounts retain tool access

CVE-2026-62187
8.1
EPSS 0.4%
Auth Bypass Privacy Violation Agent Plugin
openclaw\/feishu CWE-863 3 3 ATLAS
HIGH

OpenClaw: model override bypasses admin authorization

CVE-2026-62186
7.6
EPSS 0.3%
Auth Bypass Agent API
openclaw CWE-862 3 3 ATLAS
UNKNOWN

Ollama: downloadBlob array index bug enables unauth DoS

CVE-2026-15685
--
EPSS 0.7%
DoS Inference
ollama CWE-129 1.8K 2 ATLAS
HIGH

vLLM Gateway: logs leak bearer tokens & chat PII

CVE-2026-15574
7.5
EPSS 0.4%
Data Leakage Privacy Violation Inference API
CWE-538 3 ATLAS
MEDIUM EXPLOIT AVAIL

HashNeRF: torch.load deserialization allows local RCE

CVE-2026-15531
5.3
EPSS 0.3%
Code Execution Supply Chain Model Framework
CWE-20 3 ATLAS
MEDIUM EXPLOIT AVAIL

n8n-workflow-builder: path traversal via filePath arg

CVE-2026-15521
5.3
EPSS 0.2%
Data Leakage Code Execution Agent Plugin
CWE-22 2 ATLAS
CRITICAL

Flowise: hardcoded JWT secrets enable full auth bypass

CVE-2026-56271
9.8
EPSS 0.7%
Auth Bypass Privacy Violation Code Execution Agent Framework API
Flowise CWE-321 3 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: RCE via unsandboxed LLM code execution

CVE-2026-61447
10.0
EPSS 2.5%
Prompt Injection Code Execution Agent
praisonai CWE-94 1 5 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: AICoder root RCE via unsanitized tool calls

CVE-2026-61445
9.9
EPSS 0.9%
Code Execution Prompt Injection Agent Plugin
praisonai CWE-22 1 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI Platform: workspace members bypass owner authz

CVE-2026-61442
7.1
EPSS 0.5%
Auth Bypass Agent Framework
CWE-862 2 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: umbral de bloqueo mal configurado permite prompt injection

CVE-2026-61439
7.5
EPSS 0.4%
Prompt Injection Data Extraction Auth Bypass Agent Framework
praisonai CWE-1188 1 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: SSRF bypass via DNS rebinding/redirects

CVE-2026-61429
8.5
EPSS 0.3%
Data Leakage Auth Bypass Agent Plugin
praisonai CWE-918 1 3 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: webhook signature bypass enables spoofing

CVE-2026-61428
7.3
EPSS 0.4%
Auth Bypass Prompt Injection Social Engineering Agent Plugin
praisonai CWE-290 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: insecure defaults expose agent secrets

CVE-2026-61426
8.6
EPSS 0.5%
Auth Bypass Data Leakage Data Extraction Agent API
praisonai CWE-200 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: SQL/CQL injection via unvalidated vector dim

CVE-2026-60090
9.8
EPSS 0.7%
Code Execution Data Leakage DoS RAG Agent Framework
praisonai CWE-89 1 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: path traversal leaks files into LLM prompts

CVE-2026-60088
5.5
EPSS 0.2%
Data Leakage Privacy Violation Agent Framework
praisonai CWE-22 1 3 ATLAS
MEDIUM

Drupal module CSRF flaw; unrelated to Ray ML framework

CVE-2026-15080
4.3
EPSS 0.1%
Auth Bypass Plugin
LOW

Drupal OpenAI Provider: SSRF via unvalidated API endpoint

CVE-2026-13233
3.3
EPSS 0.2%
Data Leakage Auth Bypass Plugin API
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