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
3,024

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 3024 results
MEDIUM

openclaw: path traversal exposes host files via audio embed

GHSA-gfg9-5357-hv4c
--
Prompt Injection Data Extraction Agent Plugin
openclaw Patch: 2026.4.15 CWE-22 4 5 ATLAS 1 incident
MEDIUM

openclaw: auth bypass in owner command enforcement

GHSA-c28g-vh7m-fm7v
--
Auth Bypass Agent Plugin
openclaw Patch: 2026.4.21 CWE-862 4 5 ATLAS 1 incident
UNKNOWN

n8n: XML Node prototype pollution → RCE

CVE-2026-42232
--
EPSS 0.5%
Code Execution Data Extraction Agent Plugin Framework
n8n Patch: 2.18.1 CWE-1321 16 5 ATLAS
UNKNOWN

n8n: prototype pollution → RCE via Git node SSH

CVE-2026-42231
--
EPSS 0.9%
Code Execution Supply Chain Agent Plugin
n8n Patch: 1.123.32 CWE-1321 16 6 ATLAS
UNKNOWN

n8n: stored XSS via MCP OAuth steals agent sessions

CVE-2026-42235
--
EPSS 0.3%
Code Execution Data Extraction Auth Bypass Agent Plugin Framework
n8n Patch: 1.123.32 CWE-87 16 7 ATLAS
UNKNOWN

n8n: IDOR exposes cross-user API key exfiltration

CVE-2026-42226
--
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation Agent API Framework
n8n Patch: 2.17.5 CWE-862 16 6 ATLAS
UNKNOWN

n8n: Python sandbox escape enables container RCE

CVE-2026-42234
--
EPSS 0.4%
Code Execution Supply Chain Data Extraction Agent Framework Plugin
n8n Patch: 1.123.32 CWE-94 16 5 ATLAS
UNKNOWN

n8n: IDOR leaks cross-project variables via API key

CVE-2026-42227
--
EPSS 0.2%
Auth Bypass Data Extraction Agent API
n8n Patch: 1.123.32 CWE-639 16 4 ATLAS
UNKNOWN

n8n: unauthenticated MCP endpoint causes memory DoS

CVE-2026-42236
--
EPSS 0.5%
DoS Agent Framework
n8n Patch: 1.123.32 CWE-770 16 3 ATLAS
UNKNOWN

n8n: WebSocket auth bypass hijacks AI agent workflows

CVE-2026-42228
--
EPSS 0.4%
Auth Bypass Data Extraction Prompt Injection Agent Framework Plugin
n8n Patch: 1.123.32 CWE-862 16 5 ATLAS
UNKNOWN

n8n: SQL injection in SeaTable node leaks restricted rows

CVE-2026-42229
--
EPSS 0.3%
Data Extraction Auth Bypass Agent Plugin
n8n Patch: 1.123.32 CWE-89 16 4 ATLAS
UNKNOWN

n8n: MCP OAuth open redirect enables phishing

CVE-2026-42230
--
EPSS 0.2%
Social Engineering Auth Bypass Agent API
n8n Patch: 1.123.32 CWE-601 16 4 ATLAS
UNKNOWN

n8n: SQL injection in Oracle node allows data exfiltration

CVE-2026-42233
--
EPSS 0.3%
Data Extraction Code Execution Agent Framework
n8n Patch: 1.123.32 CWE-20 16 4 ATLAS
UNKNOWN

n8n: SQL injection in Snowflake/MySQL nodes bypasses fix

CVE-2026-42237
--
EPSS 0.3%
Code Execution Data Extraction Agent Plugin
n8n Patch: 1.123.32 CWE-89 16 4 ATLAS
CRITICAL

Ollama: path traversal + unsigned update = silent RCE

CVE-2026-42249
9.8
EPSS 0.6%
Code Execution Supply Chain Inference
ollama CWE-22 1.7K 4 ATLAS
CRITICAL

Ollama: silent auto-update bypasses signature check on Windows

CVE-2026-42248
9.8
EPSS 0.4%
Supply Chain Code Execution Inference
ollama CWE-494 1.7K 5 ATLAS
MEDIUM EXPLOIT AVAIL

vllm: uninitialized KV cache memory leaks inference data

CVE-2026-7141
5.6
EPSS 0.3%
Data Leakage DoS Inference Framework
vllm Patch: 0.19.1 CWE-908 130 4 ATLAS
LOW EXPLOIT AVAIL

Ollama: path traversal in tensor model transfer handler

CVE-2026-7020
3.7
EPSS 0.9%
Data Extraction Code Execution Inference Model
ollama CWE-22 1.7K 4 ATLAS
MEDIUM

openclaw: config guard bypass, persistent settings mutation

GHSA-7jm2-g593-4qrc
--
Prompt Injection Auth Bypass Agent Framework Plugin
openclaw Patch: 2026.4.20 CWE-285 4 4 ATLAS 1 incident
MEDIUM

openclaw: tool policy bypass via bundled MCP/LSP tools

GHSA-qrp5-gfw2-gxv4
--
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.4.20 CWE-862 4 4 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