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 983 results — Medium severity, no patch
MEDIUM

TensorRT-LLM: reachable assertion crashes sampler thread

CVE-2026-47475
6.2
EPSS 0.2%
DoSInferenceAPI
CWE-6172 ATLAS
MEDIUM

TensorRT-LLM: unthrottled GPU allocation causes DoS

CVE-2026-24271
6.2
EPSS 0.2%
DoSInferenceAPI
CWE-7703 ATLAS
MEDIUM

OpenClaw: web search auth bypass enables restricted ops

CVE-2026-62198
5.4
EPSS 0.3%
Auth BypassAgentPlugin
openclawCWE-86332 ATLAS
MEDIUM

OpenClaw: auth bypass in plugin install wrapper

CVE-2026-62193
6.5
EPSS 0.3%
Auth BypassSupply ChainAgentPlugin
openclawCWE-86333 ATLAS1 incident
MEDIUMEXPLOIT AVAIL

HashNeRF: torch.load deserialization allows local RCE

CVE-2026-15531
5.3
EPSS 0.3%
Code ExecutionSupply ChainModelFramework
CWE-203 ATLAS
MEDIUMEXPLOIT AVAIL

n8n-workflow-builder: path traversal via filePath arg

CVE-2026-15521
5.3
EPSS 0.2%
Data LeakageCode ExecutionAgentPlugin
CWE-222 ATLAS
MEDIUM

Drupal module CSRF flaw; unrelated to Ray ML framework

CVE-2026-15080
4.3
EPSS 0.1%
Auth BypassPlugin
MEDIUM

Grafana: stored XSS via malicious TableNG field name

CVE-2026-8595
5.4
EPSS 0.2%
Code ExecutionPrivacy ViolationAuth BypassInferencePlugin
2 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: IDOR lets members delete owner dependencies

CVE-2026-61441
6.5
EPSS 0.3%
Auth BypassAgentFramework
CWE-8621 ATLAS
MEDIUM

n8n: stored XSS + phishing redirect in Form Node

CVE-2026-56354
5.4
EPSS 0.2%
Social EngineeringCode ExecutionAgentPlugin
n8nCWE-79161 ATLAS
MEDIUM

GitHub CLI: command execution via malicious Codespace URI

CVE-2026-59831
4.4
EPSS 0.3%
Code ExecutionSupply ChainFramework
CWE-8293 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: broken access control leaks private note data

CVE-2026-59853
6.5
EPSS 0.3%
Auth BypassData LeakageAPI
CWE-8621 ATLAS
MEDIUMEXPLOIT AVAIL

OpenClaw Android: command injection via WebView bridge

CVE-2026-15193
5.3
EPSS 1.1%
Code ExecutionAgentPlugin
CWE-773 ATLAS
MEDIUMEXPLOIT AVAIL

pyload-ng: IPv6 SSRF bypass evades internal-IP guard

CVE-2026-48737
4.9
EPSS 0.3%
Auth BypassData LeakageAgentPlugin
pyload-ngCWE-9185122 ATLAS
MEDIUM

Easy Invoice (WP): missing authz on quote accept/decline

CVE-2026-9021
5.3
EPSS 0.5%
Auth BypassPlugin
MEDIUM

OpenClaw: dotenv override leaks provider credentials

CVE-2026-59261
6.5
EPSS 0.3%
Data LeakageAuth BypassSupply ChainAgentFramework
openclawCWE-18434 ATLAS
MEDIUM

TrustyAI: missing auth exposes guardrails orchestrator

CVE-2026-15044
6.3
EPSS 0.2%
Auth BypassData LeakageFrameworkInference
nemoguardrails103 ATLAS
MEDIUMEXPLOIT AVAIL

AVideo Meet: stored XSS via unescaped User-Agent

CVE-2026-60092
6.1
EPSS 0.3%
Code ExecutionAuth BypassPlugin
1 ATLAS
MEDIUM

n8n: workflow:read scope triggers executions via API

CVE-2026-56778
6.4
EPSS 0.3%
Auth BypassAgentAPI
n8n162 ATLAS
MEDIUM

n8n: viewer role bypasses RBAC on eval test runs

CVE-2026-56775
5.4
EPSS 0.3%
Auth BypassDoSAgentFramework
n8n161 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