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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1295 results — High severity, no patch
HIGHEXPLOIT AVAIL

Flowise: RCE via CSVAgent unsanitized code injection

CVE-2026-41137
8.8
EPSS 1.5%
Code ExecutionData ExtractionAgentFramework
flowise4 ATLAS
HIGH

engramx: CSRF injects persistent prompts into AI agents

GHSA-2r2p-4cgf-hv7h
--
Prompt InjectionData ExtractionAuth BypassAgentPlugin
CWE-3065 ATLAS
HIGH

InstructLab: RCE via hardcoded trust_remote_code flag

CVE-2026-6859
8.8
EPSS 0.4%
Supply ChainCode ExecutionModelTraining Data
instructlabCWE-8295 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

LangChain-ChatChat: RCE via unauthenticated MCP interface

CVE-2026-30617
8.6
EPSS 0.5%
Code ExecutionAuth BypassSupply ChainAgentFrameworkPlugin
6 ATLAS
HIGH

mcp-ssh: argument injection enables LLM-driven local RCE

GHSA-p4h8-56qp-hpgv
--
Code ExecutionPrompt InjectionData ExtractionAgentPlugin
CWE-786 ATLAS
HIGH

OpenClaw: privilege escalation via plugin scope bypass

CVE-2026-35669
8.8
EPSS 0.3%
Auth BypassData ExtractionAgentPlugin
OpenClaw35 ATLAS1 incident
HIGHEXPLOIT AVAIL

OpenClaw: sandbox path traversal exposes agent secrets

CVE-2026-35668
7.7
EPSS 0.4%
Data ExtractionAuth BypassAgentFramework
OpenClaw35 ATLAS1 incident
HIGH

OpenClaw: allowlist bypass enables arbitrary command exec

CVE-2026-35666
8.8
EPSS 0.4%
Auth BypassCode ExecutionAgentPlugin
OpenClaw34 ATLAS1 incident
HIGHEXPLOIT AVAIL

OpenClaw: privilege escalation to admin via backend reconnect

CVE-2026-35663
8.8
EPSS 0.3%
Auth BypassCode ExecutionAgent
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: auth bypass allows admin session hijacking

CVE-2026-35660
8.1
EPSS 0.3%
Auth BypassData ExtractionAgent
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: auth bypass enables agent profile destruction

CVE-2026-35653
8.1
EPSS 0.6%
Auth BypassDoSAgent
OpenClaw35 ATLAS1 incident
HIGH

OpenClaw: env var override bypass enables code execution

CVE-2026-35650
7.5
EPSS 0.5%
Code ExecutionAuth BypassAgentFramework
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: WebView bridge injection enables Android RCE

CVE-2026-35643
8.8
EPSS 0.4%
Code ExecutionAuth BypassAgentPlugin
OpenClaw35 ATLAS1 incident
HIGH

OpenClaw: RCE via .npmrc override in plugin install

CVE-2026-35641
7.8
EPSS 0.1%
Supply ChainCode ExecutionAgentPlugin
OpenClaw34 ATLAS1 incident
HIGHEXPLOIT AVAIL

PraisonAI: unauth WebSocket drains OpenAI API credits

CVE-2026-40116
7.5
EPSS 0.4%
Auth BypassDoSAgentAPI
praisonaiCWE-77015 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: arg injection injects env vars into Cloud Run

CVE-2026-40113
8.4
EPSS 0.2%
Code ExecutionSupply ChainAuth BypassAgentFramework
praisonaiCWE-8814 ATLAS
HIGH

OpenClaw: privilege escalation via synthetic admin session scope

CVE-2026-35645
8.1
EPSS 0.3%
Auth BypassCode ExecutionAgentPlugin
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: scope bypass enables admin RCE via device pairing

CVE-2026-35639
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgentAPIFramework
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: priv escalation via trusted-proxy scope bypass

CVE-2026-35638
8.8
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
OpenClaw34 ATLAS1 incident

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