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
3,018

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 1942 results — no patch
MEDIUM

JupyterLab before 4.5.9 contains a stored cross-site scripting vulnerability in the Extension Manager that fails to validate URI protocols in package metadata...

CVE-2026-67338
6.1
EPSS 0.2%
CWE-84
CRITICAL

ComfyUI: unauthenticated RCE via pickle upload

CVE-2026-68771
9.8
EPSS 0.6%
Code Execution Supply Chain Training Data Framework
CWE-502 4 ATLAS
CRITICAL

sentence-transformers: trust gate bypass enables RCE

CVE-2026-68770
9.8
EPSS 0.5%
Auth Bypass Code Execution Supply Chain Model Inference Framework
sentence-transformers CWE-94 3.1K 4 ATLAS
HIGH

Pterodactyl Wings: SFTP handshake DoS via Go panic

CVE-2026-52856
7.5
EPSS 0.3%
DoS Framework
CWE-129
MEDIUM

Pterodactyl Wings: config parser DoS exhausts memory

CVE-2026-52857
5.5
EPSS 0.1%
DoS
MEDIUM

pgAdmin: broken access control bypasses tool permissions

CVE-2026-17350
5.4
EPSS 0.2%
Auth Bypass Code Execution RAG
1 ATLAS
MEDIUM

Dynatrace MCP: Jinja injection creates persistent exfil

GHSA-xrmj-5g4g-8987
4.2
Prompt Injection Data Leakage Code Execution Agent Plugin API
CWE-1336 3 ATLAS
MEDIUM

Dynatrace MCP server: DQL injection bypasses read-tool caps

GHSA-pqh8-p93p-2rx7
4.3
Prompt Injection Data Leakage Auth Bypass Agent Plugin API
CWE-943 3 ATLAS
MEDIUM

Apache Zeppelin: path traversal escapes notebook root

CVE-2026-44615
6.5
EPSS 0.5%
Code Execution DoS Framework
CWE-22 2 ATLAS
AWAITING NVD

Google mcp-toolbox: BigQuery allowedDatasets bypass

CVE-2026-14538
--
EPSS 0.2%
Auth Bypass Data Extraction Data Leakage Agent Plugin API
3 ATLAS
CRITICAL EXPLOIT AVAIL

OpenClaw Dashboard: stored XSS enables admin takeover

CVE-2026-66421
9.3
EPSS 0.4%
Code Execution Auth Bypass Data Leakage Agent Framework
openclaw-dashboard CWE-79 4 3 ATLAS
HIGH

MeshCentral: origin-check bypass lets attackers hijack admin sessions

CVE-2026-66420
8.8
EPSS 0.2%
Auth Bypass Data Leakage Code Execution Agent
openclaw-dashboard 4 4 ATLAS
CRITICAL EXPLOIT AVAIL

OpenClaw: stored XSS via login field hijacks admin

CVE-2026-66418
9.3
EPSS 0.3%
Code Execution Auth Bypass Agent Framework
openclaw CWE-79 4 3 ATLAS
CRITICAL

Langflow: unsanitized code input enables RCE

CVE-2026-12946
9.9
EPSS 0.4%
Code Execution Auth Bypass Framework Agent
langflow 2 ATLAS
CRITICAL EXPLOIT AVAIL

SGLang: RCE via unsafe pickle deserialization on weight load

CVE-2026-15976
9.8
EPSS 0.3%
Code Execution Supply Chain Inference Model Framework
4 ATLAS
HIGH

Langflow: IDOR exposes/poisons cross-tenant RAG vectors

CVE-2026-13444
8.1
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation Framework RAG Plugin
langflow CWE-520 3 ATLAS
HIGH

Langflow: IDOR exposes/manipulates other users' builds

CVE-2026-12945
7.1
EPSS 0.2%
Auth Bypass Data Leakage Framework Agent
langflow CWE-639 2 ATLAS
CRITICAL

Langflow: unauth RCE via MCP env var injection

CVE-2026-12940
9.8
EPSS 0.5%
Code Execution Framework Agent Plugin
langflow CWE-78 4 ATLAS
MEDIUM

Langflow: IDOR in file API leaks cross-tenant data

CVE-2026-10700
6.5
EPSS 0.4%
Auth Bypass Data Leakage Framework API
Langflow OSS CWE-639 2 ATLAS
CRITICAL

Langflow: PythonREPL sandbox escape enables RCE

CVE-2026-13435
9.9
EPSS 0.3%
Code Execution Framework Agent Plugin
Langflow OSS CWE-94 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