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
3,027

AI/ML CVEs Tracked

424

Critical

115

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 1323 results — High severity
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, and 1.0.0...

CVE-2026-17624
8.8
EPSS 0.4%
CWE-94
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3 does not properly validate ownership in the deprecated POST /api/v1/build/{flow_id}/vertices endpoint, allowing an...

CVE-2026-10547
8.1
EPSS 0.2%
CWE-284
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3, and 1.0.0 through 1.10.3 contains a Server-Side Request Forgery (SSRF) vulnerability in the...

CVE-2026-9081
7.1
EPSS 0.2%
Langflow OSS
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, and 1.0.0...

CVE-2026-17625
7.2
EPSS 0.8%
Langflow OSS
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3 Langflow allows remote authenticated attackers to bypass localhost-only restrictions and write arbitrary MCP server...

CVE-2026-9077
8.5
EPSS 0.3%
CWE-807
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3 contain an authentication bypass vulnerability in the Model Context Protocol (MCP) composer endpoint when...

CVE-2026-8446
7.5
EPSS 0.3%
CWE-306
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3 could allow a remote attacker to execute arbitrary code due to improper validation of configuration parameters.

CVE-2026-17630
8.8
EPSS 0.4%
CWE-184
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3 Langflow could allow an authenticated attacker to read, modify, or expose sensitive host files via Docker-based MCP...

CVE-2026-17626
8.8
EPSS 0.3%
CWE-266
HIGH

IBM Langflow OSS 1.0.0 through 1.10.3 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of the command field...

CVE-2026-17623
8.8
EPSS 1.0%
CWE-78
HIGH

Mistral Vibe before 2.23.3 contains a remote code execution vulnerability that allows attackers to execute arbitrary commands by embedding a malicious...

CVE-2026-67623
8.8
EPSS 0.5%
mistral-vibe 387
HIGH

Hugging Face peft's LoRA-GA and CorDA initialization modules (src/peft/tuners/lora/corda.py lines ~102 and ~163, and src/peft/tuners/lora/loraga.py line ~101)...

CVE-2026-71281
8.8
EPSS 0.3%
HIGH

MLflow's AI Gateway accepts an auth_config.api_base value when creating a gateway secret (mlflow/server/handlers.py, _create_gateway_secret) with no validation...

CVE-2026-71211
7.1
EPSS 0.2%
HIGH

The AI Chatbot & Workflow Automation by AIWU plugin for WordPress is vulnerable to Sensitive Information Exposure in all versions up to, and including, 1.4.6....

CVE-2026-6639
7.5
EPSS 0.4%
CWE-862
HIGH

Open WebUI: A folder write-collaborator can permanently delete the owner's chats by deleting a shared subfolder

CVE-2026-70494
8.1
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-862 4
HIGH EXPLOIT AVAIL

Open WebUI: Stored XSS via unescaped KaTeX render-error fallback in rendered messages

CVE-2026-70492
8.7
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-79 4
HIGH

Open WebUI: Same-origin XSS to account takeover via terminal file-preview iframe hardcoding allow-same-origin

CVE-2026-70486
8.2
EPSS 0.4%
open-webui Patch: 0.11.0 CWE-79 4
HIGH EXPLOIT AVAIL

Open WebUI: Any authenticated user can reach internal services and cloud metadata via NAT64-encoded URLs

CVE-2026-70485
7.1
EPSS 0.2%
open-webui Patch: 0.11.0 CWE-918 4
HIGH EXPLOIT AVAIL

Open WebUI: Account takeover via OAuth token exchange accepting tokens issued to any client

CVE-2026-70482
8.1
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-287 4
HIGH EXPLOIT AVAIL

Open WebUI: SSRF into internal services via unvalidated sub-resource requests in the Playwright web loader

CVE-2026-70479
7.7
EPSS 0.3%
open-webui Patch: 0.11.0 CWE-918 4
HIGH EXPLOIT AVAIL

Flowise: Cross-Workspace OAuth2 Credential Metadata Leak

CVE-2026-70474
--
EPSS 0.3%
flowise Patch: 3.1.3 CWE-863

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