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 1908 results — High severity
HIGHEXPLOIT AVAIL

llama-index: SQLi+DoS via prompt injection in query engine

CVE-2024-12911
7.1
EPSS 0.5%
Prompt InjectionCode ExecutionDoSFrameworkAgent
llamaindexCWE-896 ATLAS
HIGHEXPLOIT AVAIL

Transformers: ReDoS in Nougat tokenizer causes DoS

CVE-2024-12720
7.5
EPSS 0.7%
DoSFrameworkInference
transformersCWE-13339.8K3 ATLAS
HIGHEXPLOIT AVAIL

llama-index: DoS via infinite loop in LangChain LLM

CVE-2024-12704
7.5
EPSS 0.8%
DoSFramework
llamaindexCWE-7553 ATLAS
HIGHEXPLOIT AVAIL

Ollama: DoS via malicious gguf model file upload

CVE-2024-12055
7.5
EPSS 0.8%
DoSSupply ChainInferenceModelFramework
ollama1.9K4 ATLAS
HIGHEXPLOIT AVAIL

GPT Academic: SSRF in Markdown plugin leaks credentials

CVE-2024-11031
7.5
EPSS 0.7%
Data ExtractionAuth BypassFrameworkPlugin
gpt_academic4 ATLAS
HIGHEXPLOIT AVAIL

GPT Academic: SSRF via unsanitized HotReload plugin

CVE-2024-11030
7.5
EPSS 0.7%
Data ExtractionAuth BypassFrameworkPlugin
gpt_academic4 ATLAS
HIGHEXPLOIT AVAIL

Gradio: path traversal enables arbitrary file deletion DoS

CVE-2024-10648
8.2
EPSS 0.7%
DoSSupply ChainFrameworkInference
gradioCWE-297353 ATLAS
HIGHEXPLOIT AVAIL

Gradio: ReDoS in DateTime causes CPU exhaustion DoS

CVE-2024-10624
7.5
EPSS 1.1%
DoSFrameworkInference
gradioCWE-4007353 ATLAS
HIGHEXPLOIT AVAIL

Gradio: zip bomb DoS via dataframe CSV upload

CVE-2024-10569
7.5
EPSS 0.7%
DoSFramework
gradioCWE-4757353 ATLAS
HIGH

litellm: unauthenticated DoS crashes LLM proxy server

CVE-2024-10188
7.5
EPSS 0.6%
DoSFrameworkAPIInference
litellmPatch: 1.53.1.dev1CWE-40063 ATLAS
HIGHEXPLOIT AVAIL

PyTorch: memory corruption in JIT profiler callback handler

CVE-2025-2148
7.5
EPSS 0.4%
Code ExecutionSupply ChainFrameworkInference
torchCWE-11926.1K3 ATLAS
HIGHEXPLOIT AVAIL

gpt_academic: symlink traversal exposes all server files

CVE-2025-25185
7.5
EPSS 0.6%
Data ExtractionPrivacy ViolationFramework
gpt_academic4 ATLAS
HIGH

Label Studio: SSRF via S3 endpoint exposes internal services

CVE-2025-25297
8.6
EPSS 0.7%
Data ExtractionAuth BypassFrameworkTraining Data
label-studioPatch: 1.16.0CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

Label Studio SDK: path traversal leaks server filesystem

CVE-2025-25295
--
EPSS 0.8%
Data ExtractionData LeakagePrivacy ViolationFrameworkTraining Data
label-studio-sdkPatch: 1.0.10CWE-2625 ATLAS
HIGH

vLLM: unsafe deserialization RCE via model loading

CVE-2025-24357
8.8
EPSS 0.9%
Supply ChainCode ExecutionFrameworkInferenceModel
vllmCWE-502945 ATLAS
HIGH

nbgrader: Clickjacking exposes formgrader via IFrame

CVE-2025-23205
--
EPSS 0.5%
Data ExtractionSocial EngineeringAuth BypassFramework
CWE-6684 ATLAS
HIGHEXPLOIT AVAIL

Gradio: ACL bypass via path case manipulation

CVE-2025-23042
7.5
EPSS 1.0%
Auth BypassData ExtractionFrameworkAPI
gradioCWE-1787354 ATLAS
HIGHEXPLOIT AVAIL

Lobe Chat: pre-auth SSRF leaks OpenAI API keys

CVE-2024-32965
8.6
EPSS 26.1%
Data ExtractionAuth BypassAPIFramework
6 ATLAS
HIGH

MLflow: local privilege escalation via spark_udf ToCToU

CVE-2024-27134
7.0
EPSS 0.1%
Code ExecutionAuth BypassFrameworkTraining Data
mlflowCWE-2766955 ATLAS
HIGHEXPLOIT AVAIL

Transformers: RCE via Trax model deserialization

CVE-2024-11394
8.8
EPSS 2.7%
Code ExecutionSupply ChainFrameworkModel
transformersCWE-5029.8K6 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