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
2,385

AI/ML CVEs Tracked

337

Critical

390

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 672 results — High severity, no patch
HIGH

OpenClaw: allowlist bypass enables arbitrary command exec

CVE-2026-35666
8.8
EPSS 0.4%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: privilege escalation to admin via backend reconnect

CVE-2026-35663
8.8
EPSS 0.3%
Auth Bypass Code Execution Agent
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: auth bypass allows admin session hijacking

CVE-2026-35660
8.1
EPSS 0.3%
Auth Bypass Data Extraction Agent
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: auth bypass enables agent profile destruction

CVE-2026-35653
8.1
EPSS 0.6%
Auth Bypass DoS Agent
OpenClaw 4 5 ATLAS 1 incident
HIGH

OpenClaw: env var override bypass enables code execution

CVE-2026-35650
7.5
EPSS 0.5%
Code Execution Auth Bypass Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw before 2026.3.22 contains an unvalidated WebView JavascriptInterface vulnerability allowing attackers to inject arbitrary instructions. Untrusted...

CVE-2026-35643
8.8
EPSS 0.4%
OpenClaw 4
HIGH

OpenClaw before 2026.3.24 contains an arbitrary code execution vulnerability in local plugin and hook installation that allows attackers to execute malicious...

CVE-2026-35641
7.8
EPSS 0.1%
OpenClaw 4
HIGH EXPLOIT AVAIL

PraisonAI: unauth WebSocket drains OpenAI API credits

CVE-2026-40116
7.5
EPSS 0.4%
Auth Bypass DoS Agent API
praisonai CWE-770 1 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: arg injection injects env vars into Cloud Run

CVE-2026-40113
8.4
EPSS 0.2%
Code Execution Supply Chain Auth Bypass Agent Framework
praisonai CWE-88 1 4 ATLAS
HIGH

OpenClaw before 2026.3.25 contains a privilege escalation vulnerability in the gateway plugin subagent fallback deleteSession function that uses a synthetic...

CVE-2026-35645
8.1
EPSS 0.3%
OpenClaw 4
HIGH

OpenClaw before 2026.3.22 contains a privilege escalation vulnerability in the device.pair.approve method that allows an operator.pairing approver to approve...

CVE-2026-35639
8.8
EPSS 0.5%
OpenClaw 4
HIGH

OpenClaw before 2026.3.22 contains a privilege escalation vulnerability in the Control UI that allows unauthenticated sessions to retain self-declared...

CVE-2026-35638
8.8
EPSS 0.3%
OpenClaw 4
HIGH

OpenClaw before 2026.3.22 performs cite expansion before completing channel and DM authorization checks, allowing cite work and content handling prior to final...

CVE-2026-35637
7.3
EPSS 0.2%
OpenClaw 4
HIGH

OpenClaw through 2026.2.22 contains a symlink traversal vulnerability in agents.create and agents.update handlers that use fs.appendFile on IDENTITY.md without...

CVE-2026-35632
7.1
EPSS 0.3%
OpenClaw 4
HIGH

OpenClaw before 2026.3.25 contains a privilege escalation vulnerability where silent local shared-auth reconnects auto-approve scope-upgrade requests, widening...

CVE-2026-35625
7.8
EPSS 0.2%
OpenClaw 4
HIGH

OpenClaw before 2026.3.25 contains an improper access control vulnerability in the HTTP /sessions/:sessionKey/kill route that allows any bearer-authenticated...

CVE-2026-34512
8.1
EPSS 0.3%
OpenClaw 4
HIGH

n8n-MCP: SSRF exposes cloud metadata via MCP headers

CVE-2026-39974
8.5
EPSS 0.3%
Data Extraction Data Leakage Agent Plugin
CWE-918 5 ATLAS
HIGH

Langflow: deserialization RCE via FAISS component default

CVE-2026-3357
8.8
EPSS 0.5%
Code Execution Supply Chain Framework RAG
langflow CWE-502 4 ATLAS
HIGH EXPLOIT AVAIL

text-generation-webui: unauthenticated path traversal file read

CVE-2026-35485
7.5
EPSS 0.7%
Data Extraction Auth Bypass Inference Framework
gradio CWE-22 685 3 ATLAS
HIGH EXPLOIT AVAIL

Claude Code CLI: shell injection enables RCE

CVE-2026-35021
7.8
EPSS 0.0%
Code Execution Supply Chain Agent Framework
CWE-78 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