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
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4307 results
HIGH

Langflow: IDOR leaks and poisons workflow history

CVE-2026-17627
7.1
EPSS 0.3%
Auth BypassData LeakageFrameworkAgent
langflowCWE-6393 ATLAS
MEDIUM

Langflow: path traversal exposes sensitive files

CVE-2026-17622
6.5
EPSS 0.7%
Data LeakageAuth BypassFrameworkAgent
langflowCWE-222 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file read

CVE-2026-17621
5.4
EPSS 0.4%
Data LeakageFrameworkAgent
langflowCWE-223 ATLAS
MEDIUM

Langflow: auth'd path traversal reads arbitrary files

CVE-2026-14470
6.5
EPSS 0.5%
Data LeakagePrivacy ViolationFramework
langflowCWE-223 ATLAS
HIGH

Langflow: chat attachment path traversal leaks server secrets

CVE-2026-19306
7.7
EPSS 0.5%
Data LeakagePrivacy ViolationAuth BypassFrameworkAgentPlugin
langflowCWE-223 ATLAS
HIGH

Langflow: SSRF flaw exposes internal/cloud metadata

CVE-2026-19305
7.5
EPSS 0.5%
Data LeakageAuth BypassFrameworkAgent
langflowCWE-9182 ATLAS
HIGH

Langflow: SSRF via URL parser bypass exposes internal services

CVE-2026-19304
7.7
EPSS 0.4%
Data LeakageData ExtractionFrameworkAgent
langflowCWE-9182 ATLAS
HIGH

Langflow: path traversal enables arbitrary file deletion

CVE-2026-19303
8.1
EPSS 0.6%
DoSFrameworkAgent
langflowCWE-221 ATLAS
MEDIUM

Langflow: symlink flaw leaks sensitive files

CVE-2026-19302
6.5
EPSS 0.7%
Data LeakagePrivacy ViolationFrameworkAgent
langflowCWE-221 ATLAS
MEDIUM

Langflow: SSRF allows internal network reconnaissance

CVE-2026-19301
6.5
EPSS 0.4%
Data LeakageFrameworkAgent
langflowCWE-9182 ATLAS
HIGH

Langflow: leaky credential fields expose secrets

CVE-2026-19300
7.5
EPSS 0.5%
Data LeakagePrivacy ViolationFrameworkAgent
langflow3 ATLAS
MEDIUM

Langflow: authenticated path traversal leaks files

CVE-2026-19299
6.5
EPSS 0.7%
Data LeakageData ExtractionFrameworkAgent
langflowCWE-223 ATLAS
HIGH

Langflow: auth bypass in flow build enables RCE

CVE-2026-19298
8.8
EPSS 0.9%
Auth BypassCode ExecutionFrameworkAgent
langflowCWE-943 ATLAS
MEDIUM

Langflow: header spoof bypasses MCP config write guard

CVE-2026-9186
6.5
EPSS 0.4%
Auth BypassCode ExecutionSupply ChainAgentFramework
langflowCWE-2844 ATLAS
MEDIUM

Langflow: path traversal enables arbitrary file write

CVE-2026-9138
6.5
EPSS 0.5%
Code ExecutionFrameworkAgent
langflowCWE-222 ATLAS
MEDIUM

Langflow: stored XSS in Playground chat UI

CVE-2026-8447
6.1
EPSS 0.3%
Code ExecutionData LeakageFrameworkAgent
langflowCWE-792 ATLAS
HIGHEXPLOIT AVAIL

ms-swift: unauth SSRF via multimodal media URLs

CVE-2026-85686
7.5
EPSS 0.5%
Code ExecutionData LeakageInferenceAPI
ms-swiftCWE-91862 ATLAS
HIGHEXPLOIT AVAIL

LLaMA-Factory: SSRF guard bypass via redirect/DNS rebind

CVE-2026-85673
7.5
EPSS 0.5%
Auth BypassData ExtractionAPIInference
llama-factoryCWE-9183 ATLAS
MEDIUMEXPLOIT AVAIL

tokenizers: malformed vocab crashes process (DoS)

CVE-2026-85670
6.5
EPSS 0.5%
DoSSupply ChainInferenceTraining Data
tokenizersCWE-78716.9K3 ATLAS
HIGHEXPLOIT AVAIL

OGX/Llama Stack: SSRF via MCP tool server_url

CVE-2026-85666
7.5
EPSS 0.7%
Data LeakageAuth BypassAgentAPIPlugin
llama-stackCWE-918143 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