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 3018 results
MEDIUM

The Contest Gallery WordPress plugin before 30.0.7 does not perform any capability or nonce check in one of its handlers, allowing any authenticated user down...

CVE-2026-16056
4.3
EPSS 0.2%
HIGH

python-cryptography: Duplicate self-signed intermediates can cause exponential path-building

CVE-2026-69249
--
EPSS 0.2%
cryptography Patch: 49.0.0 CWE-400 132
CRITICAL

SiYuan before v3.7.3 contains a SQL injection vulnerability in the /api/filetree/searchDocs endpoint, where the caller-supplied keyword parameter is...

CVE-2026-69085
10.0
EPSS 0.3%
CRITICAL

SiYuan versions <= v3.7.2 expose the /api/search/searchEmbedBlock endpoint, which passes a client-supplied SQL statement verbatim to the main read-write...

CVE-2026-69084
10.0
EPSS 0.3%
CWE-89
MEDIUM

SiYuan versions before v3.7.3 contain a metadata disclosure vulnerability in the /api/block/getBlockInfo endpoint that returns document root metadata including...

CVE-2026-68585
5.8
EPSS 0.2%
CRITICAL

SiYuan versions before v3.7.3 contain SQL injection vulnerabilities in the fullTextSearchAssetContent endpoint reachable by unauthenticated users and publish...

CVE-2026-69083
10.0
EPSS 0.4%
AWAITING NVD

A vulnerability in huggingface/transformers versions <=5.8.0.dev0 allows an attacker to perform arbitrary file writes via path traversal. The issue resides in...

CVE-2026-9856
--
EPSS 0.3%
CWE-22
MEDIUM

A vulnerability in keras-team/keras versions <= 3.14.0 allows arbitrary local HDF5 file content disclosure due to improper handling of HDF5 ExternalLinks. The...

CVE-2026-9335
6.5
EPSS 0.6%
keras Patch: 3.12.3 CWE-22 1.5K
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
CRITICAL

Pterodactyl Wings: egg template leaks daemon secrets

CVE-2026-52855
9.9
EPSS 0.3%
Data Leakage Auth Bypass Plugin
github.com/pterodactyl/wings Patch: 1.12.3 CWE-200 492 1 ATLAS
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
HIGH

Dynatrace MCP server: unauth HTTP data exfil via DQL

GHSA-p7w7-4929-vpj5
7.5
Auth Bypass Data Leakage Data Extraction Agent Plugin API
@dynatrace-oss/dynatrace-mcp-server Patch: 2.0.0 CWE-306 3.0K 3 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

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