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
2,377

AI/ML CVEs Tracked

337

Critical

392

New This Week

18

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 185 results — Critical severity, Active exploitation
CRITICAL EXPLOIT AVAIL

llama-index DuckDB retriever: SQLi enables RCE

CVE-2024-11958
9.8
EPSS 1.3%
Code Execution Supply Chain Data Extraction Framework RAG Plugin
llama-index-retrievers-duckdb-retriever Patch: 0.4.0 CWE-89 238 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via runner deserialization

CVE-2024-9070
9.8
EPSS 0.8%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 21 3 ATLAS
CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in RPC server

CVE-2024-9053
9.8
EPSS 1.3%
Code Execution Supply Chain Framework Inference
vllm CWE-78 130 5 ATLAS
CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in MessageQueue

CVE-2024-11041
9.8
EPSS 1.4%
Code Execution Framework Inference
vllm CWE-502 130 4 ATLAS
CRITICAL EXPLOIT AVAIL

vLLM: RCE via unsafe deserialization in Mooncake KV

CVE-2025-29783
9.0
EPSS 0.8%
Code Execution Supply Chain Framework Inference
vllm CWE-502 130 5 ATLAS
CRITICAL EXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model loading

CVE-2025-1550
9.8
EPSS 2.8%
Code Execution Supply Chain Framework Model
keras CWE-94 1.6K 6 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: ZIP flag bypass enables RCE in PyTorch models

CVE-2025-1945
9.8
EPSS 0.5%
Supply Chain Code Execution Model Framework
picklescan CWE-345 3 6 ATLAS
CRITICAL EXPLOIT AVAIL

spacy-llm: SSTI allows unauthenticated RCE (CVSS 9.8)

CVE-2025-25362
9.8
EPSS 0.7%
Code Execution Data Extraction Framework
spacy-llm Patch: 0.7.3 CWE-94 143 4 ATLAS
CRITICAL EXPLOIT AVAIL

LlamaFactory: RCE via OS command injection in training

CVE-2024-52803
9.8
EPSS 2.3%
Code Execution Supply Chain Framework Training Data
llamafactory Patch: 0.9.1 CWE-78 1 6 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: RCE via unsandboxed code component execution

CVE-2024-48061
9.8
EPSS 1.3%
Code Execution Auth Bypass Framework Agent
langflow CWE-94 5 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: Unauthenticated RCE via PythonCodeTool

CVE-2024-42835
9.8
EPSS 1.0%
Code Execution Supply Chain Data Extraction Framework Agent Plugin
langflow 6 ATLAS
CRITICAL EXPLOIT AVAIL

PyTorch: RCE via RemoteModule deserialization

CVE-2024-48063
9.8
EPSS 1.6%
Code Execution Supply Chain Framework Training Data
pytorch CWE-502 22.7K 4 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain GraphCypher: prompt injection enables DB wipe

CVE-2024-8309
9.8
EPSS 13.8%
Prompt Injection Data Extraction DoS Framework Agent RAG
langchain CWE-74 2.7K 7 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain.js: path traversal, arbitrary file read/write

CVE-2024-7774
9.1
EPSS 0.5%
Data Extraction Code Execution Data Leakage Framework Agent
langchain.js CWE-22 2.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

LangChainJS: prompt injection enables full graph DB takeover

CVE-2024-7042
9.8
EPSS 0.3%
Prompt Injection Data Extraction Code Execution Framework Agent API
langchain 2.7K 6 ATLAS
CRITICAL EXPLOIT AVAIL

Affiliator WP Plugin: Unauthenticated Web Shell Upload

CVE-2024-49326
9.8
EPSS 0.5%
Code Execution Auth Bypass Supply Chain Framework API
affiliator 1.6K 6 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain-Experimental: RCE via eval in math chain

CVE-2024-46946
9.8
EPSS 1.3%
Code Execution Supply Chain Framework Agent
langchain-experimental 2.7K 4 ATLAS
CRITICAL EXPLOIT AVAIL

streamlit-geospatial: blind SSRF via unvalidated URL input

CVE-2024-41120
9.8
EPSS 0.8%
Data Extraction Auth Bypass Framework API
streamlit-geospatial CWE-918 2.9K 3 ATLAS
CRITICAL EXPLOIT AVAIL

streamlit-geospatial: RCE via eval() on vis_params input

CVE-2024-41119
9.8
EPSS 1.4%
Code Execution Framework Inference
streamlit-geospatial 2.9K 4 ATLAS
CRITICAL EXPLOIT AVAIL

streamlit-geospatial: blind SSRF via WMS URL input

CVE-2024-41118
9.8
EPSS 0.7%
Data Extraction Auth Bypass Privacy Violation Framework API
streamlit-geospatial CWE-918 2.9K 4 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