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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 2876 results — no patch
HIGH

n8n: SeaTable Trigger leaks API token in executions

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

n8n: ReDoS in File(s) Selector glob blocks event loop

CVE-2026-118646
6.5
EPSS 0.2%
DoSAgentFramework
n8nCWE-1333163 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
MEDIUM

n8n: Chat Hub authz bypass lets chat users run tools

CVE-2026-118640
5.4
EPSS 0.2%
Auth BypassCode ExecutionAgentPluginFramework
n8nCWE-863163 ATLAS
MEDIUM

Xibo CMS: missing authz on dataset CSV export leaks data

CVE-2026-50541
6.5
EPSS 0.4%
Data LeakageAuth BypassFramework
CWE-8622 ATLAS
MEDIUM

WoowBot: missing authz lets subscribers drain AI API credits

CVE-2026-111372
4.3
EPSS 0.3%
Auth BypassDoSPluginRAGAPI
wpbotCWE-8624 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
MEDIUM

VideoLLaMA2: unverified model integrity on load

CVE-2026-116608
5.4
EPSS 0.1%
Supply ChainModel PoisoningModelInferenceFramework
VideoLLaMA21.9K3 ATLAS
AWAITING NVD

dd-trace-py: IAST % formatting error crashes process

CVE-2026-116589
--
EPSS 0.3%
DoSFrameworkAPI
CWE-2482 ATLAS
AWAITING NVD

dd-trace-py: ReDoS in query-string obfuscation causes DoS

CVE-2026-116588
--
EPSS 0.5%
DoSFrameworkAPI
CWE-13332 ATLAS
CRITICAL

TOTOLINK A950RG: command injection in firewall.so apmib_set

CVE-2026-116506
9.9
EPSS 1.9%
Code ExecutionFramework
CWE-742 ATLAS
HIGH

pgvectorscale: type confusion enables memory corruption

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