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 983 results — Medium severity, no patch
MEDIUM

n8n: approval bypass in Send and Wait chat mode

CVE-2026-103260
4.0
EPSS 0.3%
Auth BypassAgentFramework
n8nCWE-862162 ATLAS
MEDIUM

n8n: unescaped parameter interpolation exposes bulk data

CVE-2026-103258
6.8
EPSS 0.3%
Data ExtractionData LeakageAgentPluginFramework
n8nCWE-943163 ATLAS
MEDIUM

n8n: path traversal enables cross-project approval forgery

CVE-2026-103254
6.3
EPSS 0.3%
Auth BypassAgentFramework
n8nCWE-22162 ATLAS
MEDIUM

n8n: missing Webflow HMAC check allows forged triggers

CVE-2026-103245
5.3
EPSS 0.2%
Auth BypassSocial EngineeringAgentPluginAPI
n8nCWE-347163 ATLAS
MEDIUM

Redux Framework: stored XSS via user meta merge

CVE-2026-90992
6.4
EPSS 0.2%
Code ExecutionPlugin
CWE-791 ATLAS
MEDIUMEXPLOIT AVAIL

OpenClaw Windows Node: SSRF via canvas.present bypass

CVE-2026-101883
5.4
EPSS 0.3%
Auth BypassData LeakageAgentPluginFramework
openclawCWE-91832 ATLAS
MEDIUMEXPLOIT AVAIL

OpenClaw Windows Node: WebSocket memory exhaustion DoS

CVE-2026-101881
6.5
EPSS 0.4%
DoSAgentFramework
openclawCWE-77031 ATLAS
MEDIUMEXPLOIT AVAIL

OpenClaw Windows Node: missing authz allows silent camera/screen capture

CVE-2026-101879
6.5
EPSS 0.4%
Auth BypassPrivacy ViolationData LeakageAgentPluginAPI
openclawCWE-86234 ATLAS
MEDIUM

Grafana: incorrect authorization lets panels move across folders

CVE-2026-81842
4.3
EPSS 0.2%
Auth BypassFramework
1 ATLAS
MEDIUM

JupyterLab: pip option injection enables SSRF/file read

CVE-2026-102904
5.4
EPSS 0.2%
Data LeakageData ExtractionFramework
jupyterCWE-881.9K3 ATLAS
MEDIUM

JupyterLab: language pack Plural-Forms code injection

CVE-2026-102830
6.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkPlugin
jupyterCWE-791.9K4 ATLAS
MEDIUM

OpenClaw: MCP app ticket bypass lets read tokens invoke write tools

CVE-2026-102807
5.3
EPSS 0.2%
Auth BypassAgentPluginFramework
OpenClawCWE-86333 ATLAS
MEDIUM

OpenClaw: sandbox isolation bypass via media pipelines

CVE-2026-102806
6.3
EPSS 0.3%
Data LeakageAuth BypassAgentFrameworkAPI
OpenClawCWE-86333 ATLAS
MEDIUM

Langflow: eval() code injection via component options

CVE-2026-101861
4.1
EPSS 0.2%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
MEDIUMEXPLOIT AVAIL

BaoTa aaPanel: SQL injection in domain status handler

CVE-2026-101011
4.7
EPSS 0.2%
Data LeakageAuth BypassFrameworkAPI
1 ATLAS
MEDIUMEXPLOIT AVAIL

BaoTa Panel: SQL injection in log_type via getData

CVE-2026-101010
4.7
EPSS 0.2%
Data LeakageData ExtractionFramework
2 ATLAS
MEDIUMEXPLOIT AVAIL

Froxlor: CSRF on GET silently disables 2FA

CVE-2026-100712
6.5
EPSS 0.1%
Auth BypassSocial EngineeringFramework
CWE-3522 ATLAS
MEDIUM

vLLM: out-of-range stop_token_ids crash EngineCore (DoS)

CVE-2026-100654
6.5
EPSS 0.3%
DoSInferenceAPI
vllmCWE-129943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: revision pin bypass loads unpinned HF artifacts

CVE-2026-100653
6.5
EPSS 0.3%
Supply ChainInferenceFrameworkModel
vllmCWE-348943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: prompt-length bypass on disagg endpoint causes DoS

CVE-2026-100651
6.5
EPSS 0.4%
DoSInferenceAPI
vllmCWE-400943 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