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 616 results — High severity, has patch
HIGH

Flowise: unauth API exposes plaintext API keys and tokens

GHSA-4jpm-cgx2-8h37
--
Auth BypassData ExtractionData LeakageAgentFrameworkAPI
flowisePatch: 3.1.0CWE-2005 ATLAS
HIGH

Flowise: Mass Assignment allows cross-tenant org takeover

GHSA-48m6-ch88-55mj
8.1
Auth BypassData ExtractionPrivacy ViolationAgentFrameworkAPI
flowisePatch: 3.1.0CWE-205 ATLAS
HIGH

Flowise: prompt injection RCE via AirtableAgent

GHSA-f228-chmx-v6j6
8.3
Prompt InjectionCode ExecutionData ExtractionAgentFrameworkPlugin
flowise-componentsPatch: 3.1.0CWE-946 ATLAS
HIGHEXPLOIT AVAIL

Keras: safe_mode bypass allows RCE via model deserialization

CVE-2026-1462
8.8
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
kerasPatch: 3.13.2CWE-5024.1K4 ATLAS
HIGH

n8n-mcp: unauthenticated HTTP endpoints enable DoS + recon

GHSA-75hx-xj24-mqrw
8.2
Auth BypassDoSData LeakageAgentPlugin
n8n-mcpPatch: 2.47.6CWE-306165 ATLAS
HIGH

PraisonAI: untrusted tools.py import enables RCE

GHSA-g985-wjh9-qxxc
8.4
Code ExecutionSupply ChainAgentPlugin
PraisonAIPatch: 4.5.139CWE-9414 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: unauthenticated SSRF via unvalidated webhook_url

CVE-2026-40114
7.2
EPSS 0.2%
Auth BypassData ExtractionPrivacy ViolationAgentAPI
PraisonAIPatch: 4.5.128CWE-91814 ATLAS
HIGHEXPLOIT AVAIL

praisonaiagents: SSRF in web_crawl exposes cloud metadata

CVE-2026-40160
--
EPSS 0.5%
Data ExtractionPrompt InjectionAgentPlugin
praisonaiagentsPatch: 1.5.128CWE-918206 ATLAS
HIGH

praisonaiagents: CORS bypass enables silent agent RCE

GHSA-x462-jjpc-q4q4
8.1
Auth BypassCode ExecutionData ExtractionAgentFramework
praisonaiagentsPatch: 4.5.128CWE-942205 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: auto tools.py load enables local RCE

CVE-2026-40156
7.8
EPSS 0.2%
Supply ChainCode ExecutionAgentFrameworkPlugin
praisonaiPatch: 4.5.128CWE-9414 ATLAS
HIGH

PraisonAI: hardcoded approval bypass enables RCE

GHSA-qwgj-rrpj-75xm
8.8
Code ExecutionAuth BypassPrompt InjectionAgentFramework
PraisonAIPatch: 4.5.128CWE-86318 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: AST sandbox bypass enables host RCE

CVE-2026-40158
8.6
EPSS 0.2%
Code ExecutionData ExtractionAgentFramework
PraisonAIPatch: 4.5.128CWE-9415 ATLAS
HIGHEXPLOIT AVAIL

praisonaiagents: env var expansion exposes production secrets

CVE-2026-40153
7.4
EPSS 0.3%
Data ExtractionPrompt InjectionData LeakageAgentPlugin
praisonaiagentsPatch: 1.5.128CWE-526205 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: auth bypass disables agent safety controls

CVE-2026-40149
7.9
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
PraisonAIPatch: 4.5.128CWE-30614 ATLAS
HIGHEXPLOIT AVAILSCANNER

LiteLLM: RCE via bytecode rewriting in guardrails API

CVE-2026-40217
8.8
EPSS 17.0%
Code ExecutionData ExtractionInferenceFrameworkAPI
litellmPatch: 1.83.10CWE-42064 ATLAS
HIGHEXPLOIT AVAIL

PraisonAIAgents: SSRF exposes cloud metadata via web_crawl

CVE-2026-40150
7.7
EPSS 0.3%
Data ExtractionPrompt InjectionPrivacy ViolationAgentPlugin
praisonaiagentsPatch: 1.5.128CWE-918205 ATLAS
HIGH

OpenClaw: unsafe body replay on cross-origin redirect

GHSA-qx8j-g322-qj6m
--
Data ExtractionAuth BypassSupply ChainAgentPlugin
openclawPatch: 2026.4.8CWE-34535 ATLAS1 incident
HIGH

openclaw: auth bypass enables exec escalation on reconnect

GHSA-5wj5-87vq-39xm
--
Auth BypassCode ExecutionAgentPlugin
openclawPatch: 2026.4.8CWE-28834 ATLAS1 incident
HIGH

OpenClaw: env var injection enables host RCE

GHSA-7437-7hg8-frrw
--
Code ExecutionSupply ChainAgentPlugin
openclawPatch: 2026.4.8CWE-18435 ATLAS1 incident
HIGH

OpenClaw: wake hook trust violation elevates to System prompt

GHSA-jf56-mccx-5f3f
--
Prompt InjectionAuth BypassAgentPlugin
openclawPatch: 2026.4.8CWE-50136 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