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 1908 results — High severity
HIGH

openclaw: sandbox escape via host=node exec routing bypass

GHSA-736r-jwj6-4w23
--
Auth BypassCode ExecutionAgentFramework
openclawPatch: 2026.4.10CWE-86335 ATLAS1 incident
HIGH

openclaw: untrusted plugin auto-enabled during onboarding

GHSA-939r-rj45-g2rj
--
Supply ChainAuth BypassAgentPlugin
openclawPatch: 2026.4.9CWE-82934 ATLAS1 incident
HIGH

openclaw: CDP relay exposes browser DevTools on 0.0.0.0

GHSA-525j-hqq2-66r4
--
Auth BypassData ExtractionAgent
openclawPatch: 2026.4.10CWE-28434 ATLAS1 incident
HIGH

openclaw: trust bypass loads untrusted workspace plugins

GHSA-82qx-6vj7-p8m2
--
Supply ChainAuth BypassCode ExecutionAgentPluginFramework
openclawPatch: 2026.4.10CWE-86234 ATLAS1 incident
HIGH

openclaw: env denylist bypass enables code exec in agents

GHSA-vfp4-8x56-j7c5
--
Code ExecutionAuth BypassAgentPlugin
openclawPatch: 2026.4.10CWE-18434 ATLAS1 incident
HIGH

openclaw: WebSocket DoS via oversized frame ingestion

GHSA-vw3h-q6xq-jjm5
--
DoSAgent
openclawPatch: 2026.4.10CWE-40034 ATLAS1 incident
HIGH

openclaw: config redaction bypass exposes provider API keys

GHSA-8372-7vhw-cm6q
--
Data ExtractionData LeakageAuth BypassAgentAPI
openclawPatch: 2026.4.14CWE-21234 ATLAS1 incident
HIGH

Flowise: unauth TTS endpoint exposes stored AI API keys

GHSA-5fw2-mwhh-9947
--
Auth BypassData ExtractionAgentAPI
flowisePatch: 3.1.0CWE-6398 ATLAS
HIGH

Flowise: credential exposure via public chatflow API

GHSA-w47f-j8rh-wx87
--
Data ExtractionAuth BypassData LeakageAgentFrameworkAPI
flowisePatch: 3.1.07 ATLAS
HIGH

Flowise: Mass assignment enables cross-tenant store takeover

GHSA-3prp-9gf7-4rxx
--
Auth BypassData ExtractionModel PoisoningAgentRAGFramework
flowisePatch: 3.1.0CWE-2847 ATLAS
HIGH

paperclipai: connector trust bypass enables Gmail read/write

GHSA-gqqj-85qm-8qhf
8.7
Auth BypassPrivacy ViolationData ExtractionAgentPluginAPI
paperclipaiCWE-2841.8K6 ATLAS
HIGH

Paperclip: RCE via workspace runtime command injection

GHSA-w8hx-hqjv-vjcq
7.3
Code ExecutionData ExtractionSupply ChainAgentPluginFramework
@paperclipai/serverPatch: 2026.416.0CWE-771.8K8 ATLAS
HIGH

Flowise: auth bypass enables account takeover via null token

GHSA-f6hc-c5jr-878p
--
Auth BypassData ExtractionAgentFramework
flowisePatch: 3.1.0CWE-2874 ATLAS
HIGH

Flowise: Cypher injection allows full Neo4j DB wipe

GHSA-28g4-38q8-3cwc
--
Data ExtractionCode ExecutionData LeakageAgentFrameworkPlugin
flowise-componentsPatch: 3.1.0CWE-9435 ATLAS
HIGH

Flowise: HTTP reset link exposes tokens to MITM takeover

GHSA-x5w6-38gp-mrqh
--
Auth BypassData ExtractionAgentFramework
flowisePatch: 3.1.0CWE-3194 ATLAS
HIGH

Flowise: OAuth token theft via unauthenticated endpoint

GHSA-6f7g-v4pp-r667
--
Auth BypassData ExtractionPrivacy ViolationAgentFrameworkAPI
flowisePatch: 3.1.0CWE-3066 ATLAS
HIGH

FlowiseAI: SSRF via prompt injection in API Chain

GHSA-6r77-hqx7-7vw8
7.1
Prompt InjectionData ExtractionAgentFramework
flowise-componentsPatch: 3.1.0CWE-9185 ATLAS
HIGH

Flowise: SSRF bypass exposes internal services

GHSA-2x8m-83vc-6wv4
7.1
Auth BypassData ExtractionAgentFrameworkPlugin
flowise-componentsPatch: 3.1.0CWE-3675 ATLAS
HIGH

Flowise: SSRF bypass exposes cloud IAM credentials

GHSA-xhmj-rg95-44hv
7.1
Auth BypassData ExtractionCode ExecutionAgentFrameworkPlugin
flowise-componentsPatch: 3.1.0CWE-2845 ATLAS
HIGH

Flowise: MIME bypass enables persistent Node.js web shell RCE

GHSA-rh7v-6w34-w2rr
7.1
Code ExecutionAuth BypassAgentFramework
flowisePatch: 3.1.0CWE-4345 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