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
2,387

AI/ML CVEs Tracked

341

Critical

358

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 846 results — Medium severity
MEDIUM

OpenClaw: SSRF in marketplace fetch hits internal AI infra

GHSA-9q7v-8mr7-g23p
--
Supply Chain Data Extraction Auth Bypass Plugin Inference Agent
openclaw Patch: 2026.3.31 CWE-918 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

ONNX: symlink traversal reads host files via model loading

CVE-2026-34447
5.5
EPSS 0.2%
Supply Chain Data Extraction Framework Model
onnx Patch: 1.21.0 CWE-22 1.2K 5 ATLAS
MEDIUM

ONNX: hardlink path traversal leaks sensitive files

CVE-2026-34446
4.7
EPSS 0.2%
Supply Chain Data Extraction Framework Model
onnx Patch: 1.21.0 CWE-22 1.2K 4 ATLAS
MEDIUM

Anthropic SDK: TOCTOU symlink escape in async memory tool

CVE-2026-34452
--
EPSS 0.1%
Code Execution Data Extraction Auth Bypass Framework Agent API
anthropic Patch: 0.87.0 CWE-59 5.4K 5 ATLAS 17 incidents
MEDIUM

anthropic-ai/sdk: memory tool path traversal escape

CVE-2026-34451
--
EPSS 0.3%
Prompt Injection Data Extraction Code Execution Framework Agent API
@anthropic-ai/sdk Patch: 0.81.0 CWE-22 280 6 ATLAS
MEDIUM

anthropic-sdk: insecure file perms expose agent memory

CVE-2026-34450
--
EPSS 0.1%
Data Leakage Model Poisoning Data Extraction Agent Framework API
anthropic Patch: 0.87.0 CWE-276 5.4K 4 ATLAS 17 incidents
MEDIUM

OpenClaw: sandbox bypass enables arbitrary file read

CVE-2026-33581
6.5
EPSS 0.6%
Data Extraction Privacy Violation Auth Bypass Agent Plugin Framework
OpenClaw 4 5 ATLAS 1 incident
MEDIUM

OpenClaw: webhook brute-force enables event forgery

CVE-2026-33580
6.5
EPSS 0.4%
Auth Bypass Code Execution Agent API
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: allowlist bypass exposes AI agents to all users

CVE-2026-33578
4.3
EPSS 0.3%
Auth Bypass Data Extraction Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: pre-auth media fetch enables disk exhaustion DoS

CVE-2026-33576
6.5
EPSS 0.4%
Auth Bypass DoS Agent API
OpenClaw 4 3 ATLAS
MEDIUM

OpenClaw: auth bypass lets any Teams user invoke AI agent

CVE-2026-34506
4.3
EPSS 0.3%
Auth Bypass Agent Plugin
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: webhook rate-limit bypass enables brute-force

CVE-2026-34505
6.5
EPSS 0.3%
Auth Bypass Code Execution Agent
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: TOCTOU race condition enables sandbox file escape

CVE-2026-32977
6.3
EPSS 0.1%
Code Execution Auth Bypass Agent Framework
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass mutates protected agent config

CVE-2026-32976
6.5
EPSS 0.2%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: script approval bypass allows code execution

CVE-2026-32921
6.3
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 5 ATLAS 2 incidents
MEDIUM

OpenClaw: HTTP scope bypass enables model enumeration

GHSA-68f8-9mhj-h2mp
--
Auth Bypass Data Extraction API Inference
openclaw Patch: 2026.3.24 CWE-284 4 4 ATLAS 2 incidents
MEDIUM

openclaw: webhook rate-limit bypass enables token brute-force

CVE-2026-35646
4.8
EPSS 0.2%
Auth Bypass Data Extraction Agent Plugin
openclaw Patch: 2026.3.28 CWE-307 4 4 ATLAS 1 incident
MEDIUM

openclaw: unauthenticated webhook parsing enables DoS

CVE-2026-35640
5.3
EPSS 0.4%
DoS Agent
openclaw Patch: 2026.3.28 CWE-400 4 3 ATLAS
MEDIUM

openclaw: auth bypass exposes agent session history via HTTP

CVE-2026-35657
6.5
EPSS 0.2%
Auth Bypass Data Extraction Agent API
openclaw Patch: 2026.3.25 CWE-639 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: TOCTOU path traversal enables arbitrary file write

CVE-2026-33574
6.2
EPSS 0.1%
Supply Chain Code Execution Agent Plugin
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