AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

76

New This Week

16

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 684 results — High severity
HIGH

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

GHSA-rh7v-6w34-w2rr
7.1
Code Execution Auth Bypass Agent Framework
flowise Patch: 3.1.0 CWE-434 5 ATLAS
HIGH

Flowise: unauthenticated RCE via FILE-STORAGE bypass

GHSA-cvrr-qhgw-2mm6
7.7
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
flowise-components Patch: 3.1.0 CWE-20 6 ATLAS
HIGH

Flowise: unauth API exposes plaintext API keys and tokens

GHSA-4jpm-cgx2-8h37
--
Auth Bypass Data Extraction Data Leakage Agent Framework API
flowise Patch: 3.1.0 CWE-200 5 ATLAS
HIGH

Flowise: Mass Assignment allows cross-tenant org takeover

GHSA-48m6-ch88-55mj
8.1
Auth Bypass Data Extraction Privacy Violation Agent Framework API
flowise Patch: 3.1.0 CWE-20 5 ATLAS
HIGH

Flowise: prompt injection RCE via AirtableAgent

GHSA-f228-chmx-v6j6
8.3
Prompt Injection Code Execution Data Extraction Agent Framework Plugin
flowise-components Patch: 3.1.0 CWE-94 6 ATLAS
HIGH

LangChain-ChatChat: RCE via unauthenticated MCP interface

CVE-2026-30617
8.6
EPSS 0.2%
Code Execution Auth Bypass Supply Chain Agent Framework Plugin
6 ATLAS
HIGH

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

GHSA-p4h8-56qp-hpgv
--
Code Execution Prompt Injection Data Extraction Agent Plugin
CWE-78 6 ATLAS
HIGH EXPLOIT AVAIL

Keras: safe_mode bypass allows RCE via model deserialization

CVE-2026-1462
8.8
EPSS 0.1%
Supply Chain Code Execution Framework Model
keras Patch: 3.13.2 CWE-502 1.5K 4 ATLAS
HIGH

n8n-mcp: unauthenticated HTTP endpoints enable DoS + recon

GHSA-75hx-xj24-mqrw
8.2
Auth Bypass DoS Data Leakage Agent Plugin
n8n-mcp Patch: 2.47.6 CWE-306 16 5 ATLAS
HIGH

PraisonAI: untrusted tools.py import enables RCE

GHSA-g985-wjh9-qxxc
8.4
Code Execution Supply Chain Agent Plugin
PraisonAI Patch: 4.5.139 CWE-94 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: unauthenticated SSRF via unvalidated webhook_url

CVE-2026-40114
7.2
EPSS 0.0%
Auth Bypass Data Extraction Privacy Violation Agent API
PraisonAI Patch: 4.5.128 CWE-918 1 4 ATLAS
HIGH EXPLOIT AVAIL

praisonaiagents: SSRF in web_crawl exposes cloud metadata

CVE-2026-40160
--
EPSS 0.0%
Data Extraction Prompt Injection Agent Plugin
praisonaiagents Patch: 1.5.128 CWE-918 11 6 ATLAS
HIGH

praisonaiagents: CORS bypass enables silent agent RCE

GHSA-x462-jjpc-q4q4
8.1
Auth Bypass Code Execution Data Extraction Agent Framework
praisonaiagents Patch: 4.5.128 CWE-942 11 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: auto tools.py load enables local RCE

CVE-2026-40156
7.8
EPSS 0.0%
Supply Chain Code Execution Agent Framework Plugin
praisonai Patch: 4.5.128 CWE-94 1 4 ATLAS
HIGH

PraisonAI: hardcoded approval bypass enables RCE

GHSA-qwgj-rrpj-75xm
8.8
Code Execution Auth Bypass Prompt Injection Agent Framework
PraisonAI Patch: 4.5.128 CWE-863 1 8 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: AST sandbox bypass enables host RCE

CVE-2026-40158
8.6
EPSS 0.0%
Code Execution Data Extraction Agent Framework
PraisonAI Patch: 4.5.128 CWE-94 1 5 ATLAS
HIGH EXPLOIT AVAIL

praisonaiagents: env var expansion exposes production secrets

CVE-2026-40153
7.4
EPSS 0.0%
Data Extraction Prompt Injection Data Leakage Agent Plugin
praisonaiagents Patch: 1.5.128 CWE-526 11 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: auth bypass disables agent safety controls

CVE-2026-40149
7.9
EPSS 0.0%
Auth Bypass Code Execution Agent Framework
PraisonAI Patch: 4.5.128 CWE-306 1 4 ATLAS
HIGH EXPLOIT AVAIL

LiteLLM: RCE via bytecode rewriting in guardrails API

CVE-2026-40217
8.8
EPSS 0.2%
Code Execution Data Extraction Inference Framework API
litellm CWE-420 4 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAIAgents: SSRF exposes cloud metadata via web_crawl

CVE-2026-40150
7.7
EPSS 0.0%
Data Extraction Prompt Injection Privacy Violation Agent Plugin
praisonaiagents Patch: 1.5.128 CWE-918 11 5 ATLAS

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