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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 366 results — Critical severity, no patch
CRITICALEXPLOIT AVAIL

OpenAI Codex CLI: RCE via malicious MCP config files

CVE-2025-61260
9.8
EPSS 6.7%
Code ExecutionSupply ChainAgentPlugin
@openai/codexCWE-941.8K5 ATLAS
CRITICALEXPLOIT AVAIL

Claude Code: OS command injection, credential theft

CVE-2026-35022
9.8
EPSS 0.6%
Code ExecutionData ExtractionSupply ChainAgentAPIFramework
CWE-788 ATLAS
CRITICALEXPLOIT AVAIL

Budibase: Unauthenticated RCE as root via webhook

CVE-2026-35216
9.1
EPSS 10.9%
Code ExecutionAuth BypassData ExtractionFrameworkAgent
CWE-788 ATLAS
CRITICALEXPLOIT AVAILSCANNER

MLflow: auth bypass in job API enables unauthenticated RCE

CVE-2026-0545
9.1
EPSS 4.4%
Auth BypassCode ExecutionDoSFrameworkTraining Data
mlflowCWE-3066955 ATLAS
CRITICAL

OpenClaw: scope bypass escalates low-priv to admin

CVE-2026-33579
9.9
EPSS 0.8%
Auth BypassCode ExecutionAgentPlugin
OpenClaw34 ATLAS1 incident
CRITICAL

OpenClaw: RCE via unsanitized iMessage SCP paths

CVE-2026-32917
9.8
EPSS 2.0%
Code ExecutionAgent
OpenClaw33 ATLAS1 incident
CRITICAL

OpenClaw: auth bypass enables unauth agent execution

CVE-2026-32916
9.4
EPSS 0.5%
Auth BypassCode ExecutionAgentPlugin
OpenClaw35 ATLAS1 incident
CRITICAL

telnyx: PyPI supply chain attack steals cloud creds

GHSA-955r-262c-33jc
--
Supply ChainCode ExecutionData ExtractionFrameworkAPIAgent
CWE-5067 ATLAS2 incidents
CRITICAL

CrewAI: Docker sandbox fallback enables RCE

CVE-2026-2287
9.8
EPSS 0.8%
Code ExecutionAuth BypassSupply ChainAgentFrameworkPlugin
5 ATLAS1 incident
CRITICAL

CrewAI: SSRF via unvalidated RAG tool URLs exposes internal services

CVE-2026-2286
9.8
EPSS 0.5%
Data ExtractionAuth BypassPrivacy ViolationAgentRAGFramework
5 ATLAS
CRITICALEXPLOIT AVAIL

CrewAI: RCE via Docker fallback in CodeInterpreter

CVE-2026-2275
9.6
EPSS 0.5%
Code ExecutionAuth BypassAgentFrameworkPlugin
6 ATLAS1 incident
CRITICAL

OpenClaw: bootstrap code replay escalates to operator.admin

CVE-2026-32987
9.8
EPSS 0.4%
Auth BypassCode ExecutionAgentFramework
OpenClaw34 ATLAS1 incident
CRITICAL

OpenClaw: auth bypass via group name spoofing in agent

CVE-2026-32975
9.8
EPSS 0.3%
Auth BypassData ExtractionAgent
OpenClaw34 ATLAS1 incident
CRITICAL

OpenClaw: exec allowlist bypass enables RCE

CVE-2026-32973
9.8
EPSS 0.4%
Auth BypassCode ExecutionAgent
OpenClaw34 ATLAS1 incident
CRITICAL

OpenClaw: auth bypass via Feishu reaction misclassification

CVE-2026-32924
9.8
EPSS 0.3%
Auth BypassCode ExecutionAgent
OpenClaw34 ATLAS1 incident
CRITICAL

OpenClaw: privilege escalation to RCE via token scope bypass

CVE-2026-32922
9.9
EPSS 0.7%
Auth BypassCode ExecutionAgent
OpenClaw35 ATLAS1 incident
CRITICAL

litellm: supply chain attack harvests AI API credentials

GHSA-5mg7-485q-xm76
--
Supply ChainData ExtractionCode ExecutionFrameworkAPIAgent
litellmCWE-50668 ATLAS
CRITICAL

NVIDIA: Deserialization enables RCE

CVE-2025-33244
9.0
EPSS 0.6%
Code ExecutionSupply ChainData ExtractionFrameworkTraining Data
CWE-5025 ATLAS
CRITICALEXPLOIT AVAIL

langflow: security flaw enables exploitation

CVE-2026-33475
9.1
EPSS 3.2%
Supply ChainCode ExecutionData ExtractionFrameworkAgent
langflowCWE-745 ATLAS
CRITICAL

OpenClaw: auth header leak via cross-origin redirect

CVE-2026-32913
9.3
EPSS 0.3%
Data ExtractionAuth BypassData LeakageAgentAPIFramework
OpenClaw35 ATLAS1 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