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

79

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 230 results — Medium severity, Active exploitation, no patch

MEDIUM EXPLOIT AVAIL

A security flaw has been discovered in Ollama up to 0.20.2. This affects the function digestToPath of the file x/imagegen/transfer/transfer.go of the component...

CVE-2026-7020

MEDIUM EXPLOIT AVAIL

A vulnerability was detected in lm-sys fastchat up to 0.2.36. Impacted is the function add_text of the component Arena Side-by-Side View Handler. The...

CVE-2026-6608

fschat CWE-670 674

MEDIUM EXPLOIT AVAIL

A vulnerability was detected in langflow-ai langflow up to 1.8.3. The impacted element is the function get_client_ip/install_mcp_config of the file...

CVE-2026-6599

langflow CWE-74

MEDIUM EXPLOIT AVAIL

PraisonAI: XSS via no-op HTML sanitizer in agent output

CVE-2026-40112

Prompt Injection Code Execution Data Extraction Agent Framework RAG

praisonai CWE-79 1 4 ATLAS

MEDIUM EXPLOIT AVAIL

openai-realtime-ui: SSRF in API proxy endpoint

CVE-2026-5803

Data Extraction Auth Bypass API

CWE-918 3 ATLAS

MEDIUM EXPLOIT AVAIL

lollms: sessions persist after password reset

CVE-2026-1163

Auth Bypass Data Extraction API Agent

lollms CWE-613 3 ATLAS

MEDIUM EXPLOIT AVAIL

MLflow: auth bypass exposes model artifacts across experiments

CVE-2026-33866

Auth Bypass Data Extraction Framework Model

mlflow CWE-862 624 4 ATLAS

MEDIUM EXPLOIT AVAIL

smolagents: code injection via incomplete sandbox fix

CVE-2026-4963

Code Execution Supply Chain Agent Framework

smolagents CWE-74 86 5 ATLAS

MEDIUM EXPLOIT AVAIL

AI component: IDOR enables unauthorized data access

CVE-2026-30886

Data Leakage Code Execution API Model Inference

CWE-639 6 ATLAS

MEDIUM EXPLOIT AVAIL

AI component: Input Validation flaw enables exploitation

CVE-2026-4538

Model Poisoning Code Execution Framework RAG Model

MEDIUM EXPLOIT AVAIL

gradio: Weak Credentials allow account compromise

CVE-2026-27167

Supply Chain Model Poisoning Code Execution Framework Agent API

gradio CWE-522 674 8 ATLAS

MEDIUM EXPLOIT AVAIL

OpenClaw: path traversal enables arbitrary file read

CVE-2026-25475

Data Extraction Privacy Violation Supply Chain Agent Plugin

openclaw CWE-22 4 5 ATLAS 1 incident

MEDIUM EXPLOIT AVAIL

bentoml: Path Traversal enables file access

CVE-2026-24123

Supply Chain Data Extraction Framework Inference

bentoml CWE-22 22 8 ATLAS

MEDIUM EXPLOIT AVAIL

BetterDocs: Info Disclosure leaks sensitive data

CVE-2025-14980

Data Leakage Data Extraction Auth Bypass API Plugin

CWE-200 7 ATLAS

MEDIUM EXPLOIT AVAIL

AI component: Missing Auth allows unauthorized operations

CVE-2025-14371

Auth Bypass Plugin API

CWE-862 4 ATLAS

MEDIUM EXPLOIT AVAIL

local-deep-research: SSRF allows internal network access

CVE-2025-67743

Data Extraction Auth Bypass Framework API

CWE-918 4 ATLAS

MEDIUM EXPLOIT AVAIL

langflow: SSRF allows internal network access

CVE-2025-68477

Data Extraction Auth Bypass Privacy Violation Framework Agent API

langflow CWE-918 8 ATLAS

MEDIUM EXPLOIT AVAIL

AI component: SQL Injection exposes database

CVE-2025-13922

Data Extraction Auth Bypass Plugin API

MEDIUM EXPLOIT AVAIL

dspy: security flaw enables exploitation

CVE-2025-12695

Data Extraction Code Execution Framework Agent

CWE-653 5 ATLAS

MEDIUM EXPLOIT AVAIL

smolagents: security flaw enables exploitation

CVE-2025-11844

Data Extraction Auth Bypass Agent Framework Plugin

smolagents CWE-643 86 4 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