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 366 results — Critical severity, no patch
CRITICALKEVSCANNER

Langflow: token forgery + exec() chain to RCE

CVE-2026-9198
9.8
EPSS 28.7%
Auth BypassCode ExecutionFrameworkAgent
Langflow OSSCWE-944 ATLAS
CRITICAL

Langflow: unauth signup chains to RCE

CVE-2026-9202
9.8
EPSS 0.5%
Auth BypassCode ExecutionFrameworkAgent
Langflow OSSCWE-3064 ATLAS
CRITICALEXPLOIT AVAIL

AVideo: stored XSS in YPTSocket enables admin takeover

CVE-2026-54458
9.6
EPSS 0.4%
Code ExecutionAuth BypassData LeakagePlugin
CWE-791 ATLAS
CRITICALSCANNER

LiteLLM: RCE via unsanitized MCP server config

CVE-2026-30623
9.8
EPSS 6.0%
Code ExecutionPluginAgentInference
litellm64 ATLAS
CRITICAL

Flowise: hardcoded JWT secrets enable full auth bypass

CVE-2026-56271
9.8
EPSS 0.7%
Auth BypassPrivacy ViolationCode ExecutionAgentFrameworkAPI
FlowiseCWE-3213 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: RCE via unsandboxed LLM code execution

CVE-2026-61447
10.0
EPSS 15.2%
Prompt InjectionCode ExecutionAgent
praisonaiCWE-9415 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: code injection via f-string in deploy API

CVE-2026-61444
9.1
EPSS 0.5%
Code ExecutionAgentFrameworkAPI
praisonaiCWE-9413 ATLAS
CRITICALEXPLOIT AVAIL

mem0: unauth config API leaks API keys + SSRF

CVE-2026-59706
9.3
EPSS 0.4%
Auth BypassData LeakageAPIFrameworkAgent
CWE-3064 ATLAS
CRITICAL

9Router: no-auth API leaks keys, chats, provider control

GHSA-vjc7-jrh9-9j86
10.0
Auth BypassData LeakagePrivacy ViolationAPIFramework
9routerCWE-2001.8K6 ATLAS
CRITICALEXPLOIT AVAIL

fickling: shared-state bug disables ML pickle allowlist check

CVE-2026-14535
9.8
EPSS 0.6%
Supply ChainCode ExecutionModelTraining Data
fickling623 ATLAS
CRITICAL

Feast: unauth file write to RCE via /save-document

CVE-2026-23537
9.1
EPSS 1.0%
Auth BypassCode ExecutionDoSAPITraining Data
rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel91.9K3 ATLAS
CRITICAL

Flowise: hardcoded default secret enables session forgery

CVE-2026-56278
9.1
EPSS 0.5%
Auth BypassCode ExecutionAgentFramework
FlowiseCWE-7985 ATLAS
CRITICAL

Langflow: weak reversible KDF exposes all stored credentials

CVE-2026-7874
9.1
EPSS 0.3%
Data LeakagePrivacy ViolationAuth BypassFrameworkAgentAPI
langflowCWE-3383 ATLAS
CRITICAL

Langflow: Redis-access deserialization enables full RCE

CVE-2026-7871
9.8
EPSS 0.7%
Code ExecutionData LeakageFrameworkAgent
langflowCWE-5024 ATLAS
CRITICAL

Langflow: malformed flow nodes enable RCE

CVE-2026-7803
9.8
EPSS 0.6%
Code ExecutionFrameworkAgent
langflowCWE-203 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: auth bypass in MCP transport exposes projects

CVE-2026-7663
9.8
EPSS 0.5%
Auth BypassData LeakageCode ExecutionFrameworkAgentPlugin
langflowCWE-2854 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: missing auth on build API leaks data, enables DoS

CVE-2026-10560
9.1
EPSS 0.5%
Auth BypassDoSData LeakageFrameworkAgent
langflowCWE-2873 ATLAS
CRITICAL

Langflow: cross-tenant API credential leak via cache bug

CVE-2026-10140
9.6
EPSS 0.4%
Auth BypassData LeakageFrameworkAPI
langflowCWE-6393 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: unauthenticated RCE via tool_code injection

CVE-2026-10134
10.0
EPSS 2.3%
Code ExecutionData LeakageAuth BypassFrameworkAgentPlugin
langflowCWE-945 ATLAS
CRITICAL

semantic-router: unpinned litellm dep pulls malware wheel

GHSA-98x5-vq43-vc5p
--
Supply ChainCode ExecutionData LeakageFrameworkInference
litellmCWE-50665 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