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 4307 results
UNKNOWN

aeon: Code injection RCE in activity dataset loader

CVE-2026-18286
--
EPSS 0.3%
Code ExecutionSupply ChainTraining DataFramework
4 ATLAS
MEDIUM

n8n: SSRF protection bypass in SearXNG Agent tool

CVE-2026-77085
--
EPSS 0.4%
Auth BypassData LeakageAgentPlugin
n8nCWE-918163 ATLAS
HIGH

n8n: RCE via unsanitized Git node config values

CVE-2026-77084
--
EPSS 0.7%
Code ExecutionSupply ChainAgentFramework
n8nCWE-78162 ATLAS
MEDIUM

n8n: Code node sandbox escape via proto pollution

CVE-2026-77083
--
EPSS 0.4%
Code ExecutionAuth BypassAgentPlugin
n8nCWE-1321162 ATLAS
MEDIUM

n8n: ReDoS in Filter/Switch nodes stalls workers

CVE-2026-77082
--
EPSS 0.5%
DoSAgent
n8nCWE-1333162 ATLAS
MEDIUM

n8n: GraphQL node allowed-domains bypass leaks creds

CVE-2026-77081
--
EPSS 0.4%
Auth BypassData LeakageAgentPlugin
n8nCWE-639163 ATLAS
HIGH

n8n: Snowflake node allows arbitrary file read/write

CVE-2026-77080
--
EPSS 0.6%
Code ExecutionData LeakageAgentPlugin
n8nCWE-78163 ATLAS
HIGH

n8n: authz bypass in role deletion grants project admin

CVE-2026-77079
--
EPSS 0.5%
Auth BypassPrivacy ViolationAgentFramework
n8nCWE-639162 ATLAS
HIGH

n8n: EventEmitter prototype pollution enables sandbox RCE

CVE-2026-77077
--
EPSS 0.6%
Code ExecutionPrivacy ViolationAgentFramework
n8nCWE-94163 ATLAS
HIGH

n8n: GraphQL error leaks decrypted credential secret

CVE-2026-77076
--
EPSS 0.5%
Data LeakagePrivacy ViolationAgentPlugin
n8nCWE-209162 ATLAS
HIGH

n8n: expression injection executes JS in victim session

CVE-2026-77075
--
EPSS 0.5%
Code ExecutionData LeakageAgentPlugin
n8nCWE-94163 ATLAS
MEDIUM

n8n: SSRF/LFI via MVG injection in Edit Image node

CVE-2026-77074
--
EPSS 0.4%
Data LeakageCode ExecutionAgentPlugin
n8nCWE-94163 ATLAS
MEDIUM

n8n: MCP auth bypass grants cross-project credentials

CVE-2026-77073
--
EPSS 0.3%
Auth BypassPrivacy ViolationAgentPlugin
n8nCWE-639164 ATLAS
HIGH

n8n: stored XSS in Form node completion page

CVE-2026-77072
--
EPSS 0.3%
Code ExecutionPrivacy ViolationAgentPlugin
n8nCWE-79162 ATLAS
HIGH

n8n: Supabase filter injection leaks/wipes full tables

CVE-2026-77071
--
EPSS 0.6%
Data ExtractionData LeakageAuth BypassAgentPluginRAG
n8nCWE-89164 ATLAS
HIGH

n8n: NoSQL injection in MongoDB node wipes/exfils data

CVE-2026-77070
--
EPSS 0.5%
Data LeakageAuth BypassAgentPlugin
n8nCWE-943163 ATLAS
LOW

n8n: SSRF bypass in OAuth2 token exchange

CVE-2026-77069
--
EPSS 0.3%
Auth BypassData LeakageAgentAPI
n8nCWE-918161 ATLAS
HIGH

n8n: RCE via path traversal in MCP schema loader

CVE-2026-77068
--
EPSS 0.9%
Code ExecutionAgentPlugin
n8nCWE-22163 ATLAS
CRITICALEXPLOIT AVAIL

LMDeploy: RCE via unauth pickle deserialization

CVE-2026-76850
9.8
EPSS 1.3%
Code ExecutionAuth BypassInferenceAPI
lmdeployCWE-50213 ATLAS
HIGH

Splunk SPL2: broken authZ lets low-priv user wipe modules

CVE-2026-76336
7.1
EPSS 0.3%
Auth BypassDoSTraining Data
CWE-8622 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