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 1577 results — no patch
MEDIUM

OpenClaw: sandbox path traversal bypasses bind isolation

CVE-2026-27523
6.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: path traversal enables arbitrary file read via media actions

CVE-2026-27522
6.5
EPSS 0.4%
Data Extraction Auth Bypass Agent
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: $SHELL env hijack enables arbitrary code execution

CVE-2026-22217
6.1
EPSS 0.1%
Code Execution Supply Chain Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: SSRF guard bypass exposes internal services

CVE-2026-22181
7.6
EPSS 0.2%
Auth Bypass Data Extraction Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: path traversal enables arbitrary file writes

CVE-2026-22180
5.3
EPSS 0.1%
Code Execution Supply Chain Agent Plugin
OpenClaw 4 5 ATLAS 1 incident
HIGH

OpenClaw: allowlist bypass enables arbitrary OS command exec

CVE-2026-22179
7.2
EPSS 0.6%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 5 ATLAS 1 incident
MEDIUM

OpenClaw versions prior to 2026.2.19 construct RegExp objects directly from unescaped Feishu mention metadata in the stripBotMention function, allowing regex...

CVE-2026-22178
6.5
EPSS 0.3%
OpenClaw 4
HIGH

OpenClaw versions prior to 2026.2.23 contain an exec approval bypass vulnerability in allowlist mode where allow-always grants could be circumvented through...

CVE-2026-22175
7.1
EPSS 0.3%
OpenClaw 4
MEDIUM

OpenClaw versions prior to 2026.2.22 inject the x-OpenClaw-relay-token header into Chrome CDP probe traffic on loopback interfaces, allowing local processes to...

CVE-2026-22174
6.8
EPSS 0.1%
OpenClaw 4
HIGH

OpenClaw versions prior to 2026.2.19 contain a path traversal vulnerability in the Feishu media download flow where untrusted media keys are interpolated...

CVE-2026-22171
8.2
EPSS 0.3%
OpenClaw 4
MEDIUM

OpenClaw versions prior to 2026.2.22 with the optional BlueBubbles plugin contain an access control bypass vulnerability where empty allowFrom configuration...

CVE-2026-22170
6.5
EPSS 0.3%
OpenClaw 4
MEDIUM

OpenClaw versions prior to 2026.2.22 contain an allowlist bypass vulnerability in the safeBins configuration that allows attackers to invoke external helpers...

CVE-2026-22169
6.7
EPSS 0.2%
OpenClaw 4
MEDIUM

OpenClaw versions prior to 2026.2.21 contain an approval-integrity mismatch vulnerability in system.run that allows authenticated operators to execute...

CVE-2026-22168
6.5
EPSS 0.4%
OpenClaw 4
UNKNOWN

GROWI: Missing Auth allows unauthorized operations

CVE-2026-25083
--
EPSS 0.3%
Prompt Injection Data Leakage Model Poisoning API RAG Inference
CWE-862 8 ATLAS
HIGH

libarchive: infinite loop DoS in RAR5 decompression

CVE-2026-4111
7.5
EPSS 0.7%
DoS Supply Chain Inference Framework
rhaiis/vllm-cuda-rhel9 130 4 ATLAS
CRITICAL EXPLOIT AVAIL

OpenClaw: RCE via request-side prompt injection

CVE-2026-30741
9.8
EPSS 0.8%
Prompt Injection Code Execution Agent Framework
openclaw 4 5 ATLAS 1 incident
MEDIUM

OpenClaw versions prior to 2026.2.17 contain a path traversal vulnerability in the $include directive resolution that allows reading arbitrary local files...

CVE-2026-32061
4.4
EPSS 0.1%
openclaw 4
CRITICAL EXPLOIT AVAIL

vllm: SSRF allows internal network access

CVE-2026-25960
9.8
EPSS 0.4%
Data Extraction Data Leakage Code Execution Inference RAG Agent
vllm CWE-918 130 7 ATLAS
CRITICAL EXPLOIT AVAIL SCANNER

Flowise: auth bypass exposes NVIDIA NIM container endpoints

CVE-2026-30824
9.8
EPSS 36.3%
Auth Bypass Code Execution Agent Inference Framework
flowise CWE-306 5 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: IDOR enables account takeover and SSO bypass

CVE-2026-30823
--
EPSS 0.4%
Auth Bypass Data Extraction Agent Framework
flowise CWE-639 5 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