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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 1295 results — High severity, no patch
HIGH

n8n: credential permission bypass leaks secrets

CVE-2026-118676
7.1
EPSS 0.2%
Auth BypassData LeakageData ExtractionAgentFrameworkPlugin
n8nCWE-863164 ATLAS
HIGH

n8n: credential guard bypass in Execute Sub-workflow

CVE-2026-118675
7.1
EPSS 0.2%
Auth BypassData LeakageAgentFramework
n8nCWE-863164 ATLAS
HIGH

n8n: prototype pollution bypasses Data Table isolation

CVE-2026-118649
8.3
EPSS 0.3%
Auth BypassData LeakageAgentFramework
n8nCWE-1321163 ATLAS
HIGH

n8n: stored XSS via webhook responses lacking CSP

CVE-2026-118648
7.3
EPSS 0.3%
Code ExecutionData LeakageFrameworkAgentPlugin
n8nCWE-79164 ATLAS
HIGH

n8n: SeaTable Trigger leaks API token in executions

CVE-2026-118647
8.2
EPSS 0.3%
Data LeakageAuth BypassAgentPluginFramework
n8nCWE-532164 ATLAS
HIGH

n8n: Quick Base node filter injection exposes records

CVE-2026-118645
8.7
EPSS 0.2%
Data LeakageData ExtractionFrameworkAgentPlugin
n8nCWE-943163 ATLAS
HIGH

n8n: error workflow inherits user identity, steals creds

CVE-2026-118644
7.7
EPSS 0.2%
Data ExtractionAuth BypassAgentFramework
n8nCWE-266164 ATLAS
HIGH

n8n: credential secrets leaked via node error data

CVE-2026-118643
8.2
EPSS 0.3%
Data LeakageData ExtractionAgentRAGPlugin
n8nCWE-209164 ATLAS
HIGH

n8n: credential permission bypass via inline sub-workflows

CVE-2026-118642
7.1
EPSS 0.2%
Auth BypassData ExtractionAgentFrameworkPlugin
n8nCWE-863165 ATLAS
HIGH

n8n: OData filter injection in Outlook/SharePoint nodes

CVE-2026-118641
7.5
EPSS 0.3%
Data ExtractionData LeakageAgentPluginFramework
n8nCWE-943163 ATLAS
HIGH

AMP for WP: stored XSS via headline shortcode attribute

CVE-2026-97019
7.2
EPSS 0.2%
Code ExecutionPlugin
CWE-791 ATLAS
HIGH

dd-trace: ReDoS in query string obfuscation causes DoS

CVE-2026-116693
--
EPSS 0.4%
DoSAPIFramework
CWE-13332 ATLAS
HIGH

Strands Agents: symlink flaw enables file overwrite, session tampering

GHSA-3w55-933p-8pv5
7.1
Code ExecutionPrompt InjectionSupply ChainFrameworkAgent
CWE-594 ATLAS
HIGH

ATXP Gemini CLI ext: command injection via MCP tools

CVE-2026-117560
7.8
EPSS 0.7%
Code ExecutionPrompt InjectionSupply ChainPluginAgent
gemini-cli-extension4 ATLAS
HIGH

Mistral Vibe: RCE via git filter drivers in worktree

CVE-2026-116843
8.8
EPSS 0.4%
Code ExecutionSupply ChainAgentFramework
mistral-vibe4733 ATLAS
HIGH

pgvectorscale: type confusion enables memory corruption

CVE-2026-116489
7.5
EPSS 0.5%
Code ExecutionData LeakageDoSRAGFramework
CWE-8433 ATLAS
HIGH

vLLM: uninitialized tensor lets tenant crash engine

CVE-2026-116180
7.7
EPSS 0.3%
DoSInferenceFramework
vllmCWE-908943 ATLAS
HIGH

vLLM: num_frames override enables memory-exhaustion DoS

CVE-2026-116179
7.5
EPSS 0.3%
DoSInferenceAPI
vllmCWE-770944 ATLAS
HIGH

vLLM: multimodal metadata DoS crashes inference engine

CVE-2026-116178
7.5
EPSS 0.3%
DoSInferenceAPI
vllmCWE-20943 ATLAS
HIGH

vLLM: decompression bomb in Nemotron-VL causes DoS

CVE-2026-116177
7.5
EPSS 0.3%
DoSInferenceAPIModel
vllmCWE-400944 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