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
3,628

AI/ML CVEs Tracked

484

Critical

101

New This Week

25

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 338 results — Critical severity, no patch
CRITICAL

Mistral Vibe: quoted paths bypass file read guard

CVE-2026-87983
--
EPSS 0.4%
Auth Bypass Data Leakage Agent
mistral-vibe 492 3 ATLAS
CRITICAL

Langflow: unauthenticated RCE via code injection

CVE-2026-81204
9.8
EPSS 0.6%
Code Execution Supply Chain Framework Agent
langflow CWE-94 2 ATLAS
CRITICAL

Langflow: unauthenticated OS command injection (CVSS 9.8)

CVE-2026-79724
9.8
EPSS 0.5%
Code Execution Framework Agent
langflow CWE-78 3 ATLAS
CRITICAL

Langflow: unauth RCE via public MCP endpoints

CVE-2026-85025
9.8
EPSS 0.4%
Auth Bypass Code Execution Data Leakage Framework Agent Plugin
langflow CWE-863 3 ATLAS
CRITICAL

Flowise: unauthenticated RCE via prediction API endpoint

CVE-2026-52098
9.8
EPSS 0.8%
Code Execution Auth Bypass Agent Framework
flowise 3 ATLAS
CRITICAL

Gemini CLI: RCE via malicious .env GEMINI_CLI_HOME override

CVE-2026-13745
--
EPSS 0.3%
Code Execution Supply Chain Agent Plugin
run-gemini-cli GitHub Action 4 ATLAS
CRITICAL

Codex Desktop: Git config filter triggers sandbox-escape RCE

CVE-2026-19593
9.8
EPSS 0.3%
Code Execution Auth Bypass Privacy Violation Agent
Codex Desktop 1.2K 3 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: auth'd RCE bypasses custom-component block

CVE-2026-19295
9.9
EPSS 1.8%
Code Execution Auth Bypass Framework Agent
langflow CWE-95 3 ATLAS
CRITICAL

Langflow: unauthenticated RCE via A2A endpoint

CVE-2026-19286
9.8
EPSS 0.6%
Auth Bypass Code Execution Framework Agent
langflow CWE-94 3 ATLAS
CRITICAL EXPLOIT AVAIL

crewai-tools: Path traversal in FileWriterTool enables RCE

CVE-2026-37007
9.8
EPSS 0.7%
Code Execution Supply Chain Agent Plugin Framework
4 ATLAS
CRITICAL EXPLOIT AVAIL

Cohere North AI: file upload flaw enables RCE

CVE-2025-61165
9.8
EPSS 0.4%
Code Execution Agent RAG
3 ATLAS
CRITICAL EXPLOIT AVAIL

Cohere North AI: missing Origin check enables CSWSH

CVE-2025-61163
9.8
EPSS 0.3%
Auth Bypass Data Leakage Agent API
3 ATLAS
CRITICAL

DrayTek VigorAP: pre-auth UDP command injection to root

CVE-2026-71914
9.8
EPSS 3.1%
Code Execution Plugin
CRITICAL

Headroom LLM proxy: IDOR exposes cross-user memory

CVE-2026-77776
9.1
EPSS 0.3%
Auth Bypass Data Leakage Privacy Violation API Agent
3 ATLAS
CRITICAL EXPLOIT AVAIL

LMDeploy: RCE via unauth pickle deserialization

CVE-2026-76850
9.8
EPSS 1.0%
Code Execution Auth Bypass Inference API
lmdeploy CWE-502 1 3 ATLAS
CRITICAL

Langflow: sin límite de intentos permite account takeover

CVE-2026-19297
9.1
EPSS 0.4%
Auth Bypass Privacy Violation Framework Agent
langflow CWE-307 2 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: RCE via Custom MCP node env var injection

CVE-2026-73601
--
EPSS 0.9%
Code Execution Agent Plugin Framework
Flowise CWE-95 3 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: Python sandbox bypass enables unauth RCE

CVE-2026-73487
--
EPSS 1.0%
Prompt Injection Code Execution Data Extraction Agent Framework
Flowise CWE-94 4 ATLAS
CRITICAL

Flowise: RCE via Airtable Agent pyodide sandbox bypass

CVE-2026-73485
--
EPSS 0.6%
Code Execution Auth Bypass Prompt Injection Agent Plugin Framework
Flowise CWE-94 5 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: sandbox escape via puppeteer.launch() to RCE

CVE-2026-73483
--
EPSS 0.6%
Code Execution Data Leakage Agent Plugin
Flowise CWE-78 4 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