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
3,019

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 3019 results
MEDIUM

OpenClaw: agent tool call bypasses skill approval gate

GHSA-cqwv-9qjx-vxw2
5.3
Auth Bypass Supply Chain Agent Plugin
openclaw Patch: 2026.5.6 CWE-807 4 3 ATLAS 2 incidents
HIGH

OpenClaw: QQBot command bypasses config allowlist

GHSA-jvm4-4j77-39p6
--
Auth Bypass Privacy Violation Agent Plugin
openclaw Patch: 2026.4.29 CWE-863 4 3 ATLAS
HIGH

OpenClaw: TOCTOU race bypasses node approval scope

GHSA-83w9-h5wv-j9xm
--
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.5.27 CWE-367 4 2 ATLAS
MEDIUM

OpenClaw: exec approver can bypass plugin approval gate

GHSA-wv26-j37q-2g7p
--
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.5.12 CWE-863 4 2 ATLAS 1 incident
MEDIUM

OpenClaw: memory-wiki ingest reads arbitrary local files

GHSA-p2fh-f5fc-44hr
6.5
Data Leakage Privacy Violation Auth Bypass Plugin Agent
openclaw Patch: 2026.5.12 CWE-732 4 3 ATLAS
HIGH

OpenClaw: chat.send routing bypasses admin auth scopes

GHSA-hw9r-h9mr-4jff
8.8
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.5.18 CWE-862 4 3 ATLAS
HIGH

OpenClaw: safe-bin bypass exposes node-local files

GHSA-mhq8-78pj-5j79
7.1
Auth Bypass Data Leakage Agent Framework
openclaw Patch: 2026.5.18 CWE-78 4 4 ATLAS
HIGH

OpenClaw: QQBot approval button auth bypass

GHSA-mgq6-vr84-7m2j
8.0
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.5.18 CWE-862 4 3 ATLAS
HIGH

OpenClaw: forged identity headers bypass proxy auth

GHSA-rggc-m335-3wvj
--
Auth Bypass Agent API
openclaw Patch: 2026.5.18 CWE-269 4 3 ATLAS
HIGH

OpenClaw: TOCTOU in shell wrapper bypasses command allowlist

GHSA-2j8v-hwgc-x698
--
Auth Bypass Code Execution Agent
Openclaw Patch: 2026.5.18 CWE-284 4 4 ATLAS
MEDIUM

OpenClaw: exec denylist bypass in bundled MCP loopback

GHSA-qh2f-99mv-mrcf
--
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.5.12 CWE-78 4 3 ATLAS
HIGH

OpenClaw: truncated approval UI masks exec payload

GHSA-xww8-gqvh-92x9
8.0
Auth Bypass Code Execution Social Engineering Agent Plugin
openclaw Patch: 2026.5.18 CWE-284 4 3 ATLAS 1 incident
CRITICAL

mcp-memory-service: auth bypass on document API

CVE-2026-50027
9.8
Auth Bypass Data Leakage Data Extraction API Agent RAG
mcp-memory-service Patch: 10.67.1 CWE-306 2.9K 4 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: IDOR cross-tenant data pollution

CVE-2026-58653
4.3
EPSS 0.2%
Auth Bypass Agent API
praisonai 1 2 ATLAS
HIGH

OpenAI Chatbot WP Helper: unauth content deletion

CVE-2025-69134
7.5
EPSS 0.3%
Auth Bypass DoS Plugin API
OpenAI Chatbot for WordPress – Helper CWE-862 132 1 ATLAS
UNKNOWN EXPLOIT AVAIL

MLflow: auth bypass allows cross-experiment trace access

CVE-2026-8147
--
EPSS 0.4%
Auth Bypass Data Leakage Framework API
mlflow/mlflow 674 2 ATLAS
MEDIUM

Craft CMS: entry section permission bypass

CVE-2026-50280
--
EPSS 0.3%
Auth Bypass Plugin
MEDIUM

OpenClaw: MCP SSE redirect leaks Authorization headers

GHSA-9c3v-684m-579c
6.5
Auth Bypass Data Leakage Agent Plugin
openclaw Patch: 2026.6.5 CWE-200 4 3 ATLAS 1 incident
HIGH EXPLOIT AVAIL

Gradio: path traversal in FileExplorer leaks files

CVE-2026-49119
7.5
EPSS 0.7%
Data Leakage Privacy Violation Framework
gradio CWE-22 669 3 ATLAS
HIGH

auth-fetch-mcp: SSRF bypass via IPv6 loopback

CVE-2026-49857
7.4
Auth Bypass Data Leakage Agent Plugin
auth-fetch-mcp Patch: 3.0.2 CWE-918 4 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