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 1527 results — Medium severity
MEDIUM

LangChain: path traversal exposes files outside sandbox

GHSA-gr75-jv2w-4656
5.1
Data ExtractionAuth BypassFrameworkAgent
langchain-anthropicPatch: 1.4.6CWE-223.2K4 ATLAS
MEDIUM

Nuxt: local unauth IPC leaks .env secrets on shared hosts

GHSA-534h-c3cw-v3h9
5.5
Data ExtractionData LeakageFrameworkAPI
nuxtPatch: 4.4.7CWE-2766.3K4 ATLAS
MEDIUM

Nuxt: open redirect + XSS in navigation API (SSR+client)

GHSA-c9cv-mq2m-ppp3
6.1
EPSS 0.4%
Auth BypassSocial EngineeringCode ExecutionFrameworkAPI
nuxtPatch: 4.4.7CWE-796.3K5 ATLAS
MEDIUM

OpenClaw: hostname prefix bypass leaks auth tokens

CVE-2026-53839
6.5
EPSS 0.3%
Auth BypassData ExtractionAgentFramework
OpenClawCWE-102333 ATLAS1 incident
MEDIUM

OpenClaw: auth bypass in Feishu agent binding controls

CVE-2026-53835
4.3
EPSS 0.2%
Auth BypassAgent
OpenClawCWE-86334 ATLAS1 incident
MEDIUM

OpenClaw: stale webhook secrets bypass revocation

CVE-2026-53830
6.5
EPSS 0.2%
Auth BypassData LeakageAgentAPI
OpenClawCWE-61334 ATLAS1 incident
MEDIUM

OpenClaw: SSRF leaks Gateway credentials via model metadata

CVE-2026-53827
6.5
EPSS 0.3%
Data ExtractionAuth BypassAgentFramework
OpenClawCWE-91835 ATLAS1 incident
MEDIUM

OpenClaw: workspace path leaked from sandboxed sessions

CVE-2026-53826
4.3
EPSS 0.2%
Data LeakagePrivacy ViolationAgent
OpenClawCWE-66833 ATLAS1 incident
MEDIUM

OpenClaw: path traversal exposes local files via wiki ingest

CVE-2026-53825
6.5
EPSS 0.4%
Data ExtractionData LeakageAgentRAG
OpenClawCWE-2234 ATLAS1 incident
MEDIUM

OpenClaw: stale slash tokens bypass revocation controls

CVE-2026-53824
6.5
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
OpenClawCWE-61334 ATLAS1 incident
MEDIUM

OpenClaw: exec denylist bypass via MCP session-spawn

CVE-2026-53820
6.6
EPSS 0.1%
Auth BypassCode ExecutionAgentPlugin
OpenClawCWE-86235 ATLAS1 incident
MEDIUM

typo3/html-sanitizer: XSS bypass via namespace encoding

CVE-2026-47345
--
EPSS 0.5%
Code ExecutionData ExtractionFrameworkPlugin
typo3/html-sanitizerPatch: 2.3.2CWE-796.3K4 ATLAS
MEDIUMEXPLOIT AVAIL

Budibase: SSRF via VectorDB host exposes cloud metadata

CVE-2026-48148
--
EPSS 0.2%
Data ExtractionAuth BypassRAGFramework
@budibase/serverPatch: 3.35.3CWE-9184295 ATLAS
MEDIUM

LangGraph MongoDB: NoSQL injection leaks tenant checkpoints

CVE-2026-48121
6.7
EPSS 0.4%
Data ExtractionAuth BypassData LeakageFrameworkAgent
@langchain/langgraph-checkpoint-mongodbPatch: 1.3.1CWE-9434.1K3 ATLAS
MEDIUM

Apache CXF: JWS signature bypass exposes JAX-RS APIs

CVE-2026-50634
6.5
EPSS 0.3%
Auth BypassData ExtractionAPIInference
org.apache.cxf:cxf-rt-rs-security-jose-jaxrsPatch: 4.2.2CWE-3472.6K3 ATLAS
MEDIUM

OpenClaw: MCP loopback auth bypass enables policy evasion

CVE-2026-53818
6.6
EPSS 0.1%
Auth BypassCode ExecutionData ExtractionAgentPluginFramework
openclawPatch: 2026.4.24CWE-86234 ATLAS1 incident
MEDIUM

OpenClaw: auth bypass exposes restricted channel messages

CVE-2026-53815
6.5
EPSS 0.2%
Auth BypassData ExtractionData LeakageAgentFramework
openclawPatch: 2026.5.19CWE-86237 ATLAS2 incidents
MEDIUM

OpenClaw: approval bypass enables unauthorized skill changes

CVE-2026-53808
6.5
EPSS 0.2%
Auth BypassSupply ChainAgentPlugin
OpenClawCWE-86335 ATLAS2 incidents
MEDIUM

Langflow: SSRF exposes internal ML infrastructure

CVE-2026-3341
5.4
EPSS 0.1%
Data ExtractionAuth BypassFrameworkAgent
langflowCWE-9185 ATLAS
MEDIUM

krb5: integer underflow in LDAP KDB causes heap over-read

CVE-2026-11850
5.0
DoSData LeakageFrameworkInference
rhoai/odh-mlflow-operator-rhel96951 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