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
2,404

AI/ML CVEs Tracked

347

Critical

310

New This Week

18

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 1033 results — High severity
HIGH

OpenClaw: allowlist bypass allows unauthorized shell exec

CVE-2026-53866
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
openclaw CWE-184 4 5 ATLAS
HIGH

OpenClaw: path traversal enables arbitrary local code exec

CVE-2026-53865
7.1
EPSS 0.1%
Code Execution Supply Chain Agent Framework
openclaw CWE-426 4 3 ATLAS
HIGH

OpenClaw: env var bypass enables child process code exec

CVE-2026-53864
8.1
EPSS 0.2%
Code Execution Data Extraction Auth Bypass Agent Framework Plugin
openclaw CWE-184 4 4 ATLAS
HIGH

OpenClaw: access control bypass via unvalidated group ID

CVE-2026-53863
7.1
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-639 4 3 ATLAS
HIGH

OpenClaw: env var injection loads malicious runtime deps

CVE-2026-53858
7.1
EPSS 0.1%
Supply Chain Code Execution Agent Framework
openclaw CWE-426 4 3 ATLAS
HIGH

OpenClaw: display name spoofing bypasses agent allowFrom policy

CVE-2026-53857
8.1
EPSS 0.2%
Auth Bypass Social Engineering Data Leakage Agent Framework
openclaw CWE-290 4 5 ATLAS
HIGH

OpenClaw: allowlist bypass enables shell code execution

CVE-2026-53855
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-184 4 5 ATLAS
HIGH

OpenClaw: exec allowlist bypass enables unrestricted RCE

CVE-2026-53853
8.3
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
openclaw CWE-693 4 4 ATLAS
HIGH

OpenClaw: auth bypass via Discord display name spoofing

CVE-2026-53849
8.1
EPSS 0.3%
Auth Bypass Social Engineering Agent
openclaw CWE-290 4 4 ATLAS
HIGH

OpenClaw: path traversal enables arbitrary package-manager exec

CVE-2026-53846
7.1
EPSS 0.1%
Supply Chain Code Execution Agent Framework
openclaw CWE-426 4 4 ATLAS
HIGH

OpenClaw: revocation bypass grants node token access

CVE-2026-53843
8.8
EPSS 0.3%
Auth Bypass Agent
openclaw CWE-284 4 4 ATLAS
HIGH

OpenClaw: env var injection enables arbitrary code exec

CVE-2026-53842
7.1
EPSS 0.1%
Code Execution Supply Chain Agent
openclaw CWE-426 4 5 ATLAS
HIGH

OpenClaw: credential exfiltration via MCP header forwarding

CVE-2026-53840
7.1
EPSS 0.2%
Data Leakage Data Extraction Auth Bypass Agent API Plugin
openclaw CWE-200 4 5 ATLAS
HIGH

stable-diffusion.cpp: heap overflow in .ckpt model parser

CVE-2026-47749
7.8
EPSS 0.2%
Supply Chain Code Execution Model Inference
CWE-122 4 ATLAS
HIGH

n8n: XSS via CSP bypass steals user sessions

CVE-2026-54301
--
EPSS 0.4%
Auth Bypass Code Execution Data Extraction Agent Plugin Framework
n8n Patch: 1.123.55 CWE-79 6 ATLAS
HIGH

n8n: auth bypass lets read-only users execute workflows

GHSA-hv7x-3x78-gx53
7.4
Auth Bypass Code Execution Agent Framework
n8n Patch: 1.123.55 CWE-284 4 ATLAS
HIGH EXPLOIT AVAIL

stable-diffusion.cpp: .ckpt heap overflow enables RCE

CVE-2026-47747
7.8
EPSS 0.1%
Supply Chain Code Execution Model Inference
4 ATLAS
HIGH EXPLOIT AVAIL

stable-diffusion.cpp: heap overflow via crafted .ckpt model

CVE-2026-47750
7.8
EPSS 0.1%
Supply Chain Code Execution Model Inference
5 ATLAS
HIGH

vLLM: assert bypass → RCE via poisoned HuggingFace model

CVE-2026-41523
7.5
EPSS 0.4%
Supply Chain Code Execution Inference Model
vllm Patch: 0.22.0 CWE-94 130 5 ATLAS
HIGH

Langflow: IDOR exposes cross-user LLM data and deletion

CVE-2026-33760
8.8
EPSS 0.2%
Auth Bypass Data Extraction Privacy Violation Framework Agent
langflow Patch: 1.9.0 CWE-639 4 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