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
2,385

AI/ML CVEs Tracked

337

Critical

390

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 843 results — Medium severity
MEDIUM

agentos-taskweaver: Protection Bypass circumvents security controls

GHSA-gpx9-96j6-pp87
6.5
Prompt Injection Code Execution Auth Bypass Agent Framework Plugin
agentos-taskweaver CWE-693 6 ATLAS
MEDIUM EXPLOIT AVAIL

bentoml: Path Traversal enables file access

CVE-2026-24123
6.5
EPSS 0.4%
Supply Chain Data Extraction Framework Inference
bentoml CWE-22 21 8 ATLAS
MEDIUM

chainlit: IDOR enables unauthorized data access

CVE-2025-68492
4.2
EPSS 0.2%
Auth Bypass Data Leakage Framework Agent
chainlit Patch: 2.8.5 CWE-639 40 7 ATLAS
MEDIUM

n8n: security flaw enables exploitation

CVE-2025-68949
5.3
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
n8n CWE-134 4 ATLAS
MEDIUM EXPLOIT AVAIL

BetterDocs: Info Disclosure leaks sensitive data

CVE-2025-14980
6.5
EPSS 0.3%
Data Leakage Data Extraction Auth Bypass API Plugin
CWE-200 7 ATLAS
MEDIUM

n8n: security flaw enables exploitation

CVE-2026-21894
6.5
EPSS 0.4%
Auth Bypass Code Execution Agent Framework
n8n CWE-290 6 ATLAS
MEDIUM EXPLOIT AVAIL

monai: Path Traversal enables file access

CVE-2026-21851
5.3
EPSS 0.3%
Supply Chain Code Execution Framework
monai Patch: 1.5.2 CWE-22 110 4 ATLAS
MEDIUM EXPLOIT AVAIL

AI component: Missing Auth allows unauthorized operations

CVE-2025-14371
4.3
EPSS 0.2%
Auth Bypass Plugin API
CWE-862 4 ATLAS
MEDIUM

picklescan: Code Injection enables RCE

GHSA-6556-fwc2-fg2p
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.33 CWE-94 3 6 ATLAS
MEDIUM

picklescan: Code Injection enables RCE

GHSA-cffc-mxrf-mhh4
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.33 CWE-94 3 5 ATLAS
MEDIUM

n8n: security flaw enables exploitation

CVE-2025-68697
5.4
EPSS 0.2%
Code Execution Data Extraction Data Leakage Agent Framework
n8n CWE-269 7 ATLAS
MEDIUM

n8n: XSS enables session hijacking

CVE-2025-61914
5.4
EPSS 0.2%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-79 6 ATLAS
MEDIUM EXPLOIT AVAIL

local-deep-research: SSRF allows internal network access

CVE-2025-67743
6.3
EPSS 0.3%
Data Extraction Auth Bypass Framework API
local-deep-research Patch: 1.3.9 CWE-918 4 ATLAS
MEDIUM EXPLOIT AVAIL

langflow: SSRF allows internal network access

CVE-2025-68477
6.5
EPSS 5.8%
Data Extraction Auth Bypass Privacy Violation Framework Agent API
langflow CWE-918 8 ATLAS
MEDIUM

anythingllm: Missing Auth allows unauthenticated access

CVE-2025-63390
5.3
EPSS 0.5%
Auth Bypass Data Extraction Privacy Violation API Framework Agent
7 ATLAS
MEDIUM EXPLOIT AVAIL

AI component: SQL Injection exposes database

CVE-2025-13922
6.5
EPSS 0.3%
Data Extraction Auth Bypass Plugin API
5 ATLAS
MEDIUM

taxopress: SQL Injection exposes database

CVE-2025-13359
6.5
EPSS 0.3%
Data Extraction Privacy Violation Plugin API
5 ATLAS
MEDIUM

taxopress: Missing Auth allows unauthorized operations

CVE-2025-13354
4.3
EPSS 0.2%
Auth Bypass Plugin API
4 ATLAS
MEDIUM

vllm: Resource Exhaustion enables DoS

CVE-2025-62426
6.5
EPSS 0.3%
DoS Inference API Framework
vllm CWE-770 130 4 ATLAS
MEDIUM

vllm: security flaw enables exploitation

CVE-2025-62372
6.5
EPSS 0.3%
DoS Inference Framework
vllm CWE-129 130 5 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