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
CRITICAL

litellm: supply chain attack harvests AI API credentials

GHSA-5mg7-485q-xm76
--
Supply Chain Data Extraction Code Execution Framework API Agent
litellm CWE-506 6 8 ATLAS
CRITICAL

NVIDIA: Deserialization enables RCE

CVE-2025-33244
9.0
EPSS 0.6%
Code Execution Supply Chain Data Extraction Framework Training Data
CWE-502 5 ATLAS
MEDIUM EXPLOIT AVAIL

Wallos: SSRF allows internal network access

CVE-2026-33401
6.5
EPSS 0.3%
Data Extraction Auth Bypass Privacy Violation Inference API
CWE-918 4 ATLAS
CRITICAL EXPLOIT AVAIL

langflow: security flaw enables exploitation

CVE-2026-33475
9.1
EPSS 3.0%
Supply Chain Code Execution Data Extraction Framework Agent
langflow CWE-74 5 ATLAS
CRITICAL

OpenClaw: auth header leak via cross-origin redirect

CVE-2026-32913
9.3
EPSS 0.3%
Data Extraction Auth Bypass Data Leakage Agent API Framework
OpenClaw 4 5 ATLAS 1 incident
MEDIUM

OpenClaw: sandbox escape via /acp spawn command

CVE-2026-27646
6.1
EPSS 0.1%
Auth Bypass Code Execution Agent
OpenClaw 4 4 ATLAS 2 incidents
MEDIUM

OpenClaw: shell allowlist bypass via dispatch wrapper depth

CVE-2026-27183
5.3
EPSS 0.1%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
MEDIUM EXPLOIT AVAIL

AI component: IDOR enables unauthorized data access

CVE-2026-30886
6.5
EPSS 0.3%
Data Leakage Code Execution API Model Inference
CWE-639 6 ATLAS
HIGH EXPLOIT AVAIL

AI component: Input Validation flaw enables exploitation

CVE-2026-4538
7.8
EPSS 0.2%
Model Poisoning Code Execution Framework RAG Model
CWE-20 5 ATLAS
MEDIUM

OpenClaw: sender-policy bypass injects unauthorized agent events

CVE-2026-32899
4.3
EPSS 0.2%
Auth Bypass Prompt Injection Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: ACP bypass enables silent tool execution

CVE-2026-32898
5.4
EPSS 0.3%
Auth Bypass Data Extraction Agent Framework
OpenClaw 4 4 ATLAS 1 incident
LOW

OpenClaw: auth token leak via prompt hash fallback

CVE-2026-32897
3.7
EPSS 0.3%
Auth Bypass Data Leakage Agent API
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass via webhook passwordless fallback

CVE-2026-32896
4.8
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass circumvents Slack event allowlists

CVE-2026-32895
5.4
EPSS 0.2%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
LOW

OpenClaw: auth bypass enables cross-account pairing reuse

CVE-2026-32067
3.7
EPSS 0.2%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: approval bypass enables unauthorized command exec

CVE-2026-32065
4.8
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: unauthenticated VNC access in AI sandbox

CVE-2026-32064
7.7
EPSS 0.5%
Auth Bypass Data Extraction Agent
OpenClaw 4 4 ATLAS 1 incident
LOW

OpenClaw: approval bypass enables unauthorized agent execution

CVE-2026-32058
2.6
EPSS 0.2%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 3 ATLAS 1 incident
HIGH

OpenClaw: auth bypass grants unauthorized agent control access

CVE-2026-32057
7.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: RCE via shell env var injection in system.run

CVE-2026-32056
7.5
EPSS 0.6%
Code Execution Auth Bypass Supply Chain Agent Plugin Framework
OpenClaw 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