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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 761 results — Medium severity, no patch
MEDIUM

Langflow: authenticated arbitrary file read flaw

CVE-2026-79725
6.5
EPSS 0.3%
Auth Bypass Data Leakage Framework Agent
langflow CWE-284 3 ATLAS
MEDIUM

Langflow: SSRF via unvalidated API endpoints leaks data

CVE-2026-79723
5.0
EPSS 0.3%
Data Leakage Data Extraction Framework API
langflow CWE-918 3 ATLAS
MEDIUM

Langflow: IDOR in File component leaks user files

CVE-2026-9225
6.5
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation Framework Agent Plugin
langflow CWE-639 3 ATLAS
MEDIUM SCANNER

CyberPanel: AI Scanner endpoints leak admin usernames unauthenticated

CVE-2026-87820
5.3
EPSS 0.5%
Data Leakage Auth Bypass API Plugin
CWE-200 2 ATLAS
MEDIUM

Auth0 AD/LDAP Connector: unauth local panel leaks AD creds

CVE-2026-85981
6.7
EPSS 0.1%
Auth Bypass Data Leakage Plugin
2 ATLAS
MEDIUM EXPLOIT AVAIL

Ollama: integer overflow in GGUF decoder causes DoS

CVE-2026-86289
4.3
EPSS 0.4%
DoS Supply Chain Inference Model
ollama CWE-189 1.8K 3 ATLAS
MEDIUM

RHOAI dashboard: broken authz leaks NIM/NGC secrets

CVE-2026-86332
6.5
EPSS 0.2%
Auth Bypass Data Leakage Inference API
rhoai/odh-mod-arch-mlflow-rhel9 690 2 ATLAS
MEDIUM

nbviewer: path traversal leaks notebooks/credentials

CVE-2026-86258
5.9
EPSS 0.4%
Data Leakage Auth Bypass Framework
CWE-22 2 ATLAS
MEDIUM

Langflow: authenticated SSRF exposes internal hosts

CVE-2026-17631
6.5
EPSS 0.2%
Data Leakage Privacy Violation Framework Agent
langflow CWE-918 2 ATLAS
MEDIUM

Langflow: path traversal exposes sensitive files

CVE-2026-17622
6.5
EPSS 0.5%
Data Leakage Auth Bypass Framework Agent
langflow CWE-22 2 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file read

CVE-2026-17621
5.4
EPSS 0.3%
Data Leakage Framework Agent
langflow CWE-22 3 ATLAS
MEDIUM

Langflow: auth'd path traversal reads arbitrary files

CVE-2026-14470
6.5
EPSS 0.3%
Data Leakage Privacy Violation Framework
langflow CWE-22 3 ATLAS
MEDIUM

Langflow: symlink flaw leaks sensitive files

CVE-2026-19302
6.5
EPSS 0.5%
Data Leakage Privacy Violation Framework Agent
langflow CWE-22 1 ATLAS
MEDIUM

Langflow: SSRF allows internal network reconnaissance

CVE-2026-19301
6.5
EPSS 0.3%
Data Leakage Framework Agent
langflow CWE-918 2 ATLAS
MEDIUM

Langflow: authenticated path traversal leaks files

CVE-2026-19299
6.5
EPSS 0.5%
Data Leakage Data Extraction Framework Agent
langflow CWE-22 3 ATLAS
MEDIUM

Langflow: header spoof bypasses MCP config write guard

CVE-2026-9186
6.5
EPSS 0.3%
Auth Bypass Code Execution Supply Chain Agent Framework
langflow CWE-284 4 ATLAS
MEDIUM

Langflow: path traversal enables arbitrary file write

CVE-2026-9138
6.5
EPSS 0.3%
Code Execution Framework Agent
langflow CWE-22 2 ATLAS
MEDIUM

Langflow: stored XSS in Playground chat UI

CVE-2026-8447
6.1
EPSS 0.2%
Code Execution Data Leakage Framework Agent
langflow CWE-79 2 ATLAS
MEDIUM EXPLOIT AVAIL

tokenizers: malformed vocab crashes process (DoS)

CVE-2026-85670
6.5
EPSS 0.3%
DoS Supply Chain Inference Training Data
tokenizers CWE-787 15.9K 3 ATLAS
MEDIUM

SiYuan: auth bypass leaks hidden notebook files

CVE-2026-85578
6.5
EPSS 0.3%
Auth Bypass Data Leakage RAG
CWE-862 2 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