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

95

New This Week

25

In CISA KEV

Sort:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 4307 results

Mobuy Panel: SQLi allows unauthenticated DB takeover

CVE-2024-13152

Data ExtractionAuth BypassCode ExecutionFramework

Mobuy Online Machinery Monitoring Panel5144 ATLAS

PandasAI: prompt injection enables unauthenticated RCE

CVE-2024-12366

Prompt InjectionCode ExecutionFrameworkAgent

MEDIUMEXPLOIT AVAIL

serialize-javascript: XSS via regex in AI/ML dashboards

CVE-2024-11831

Supply ChainCode ExecutionData ExtractionFrameworkPlugin

odh-kf-notebook-controller-rhel83.0K4 ATLAS

vLLM: hash collision enables prefix cache poisoning

CVE-2025-25183

Adversarial ExamplesData LeakageInferenceFramework

vllmCWE-354945 ATLAS

vLLM: unsafe deserialization RCE via model loading

CVE-2025-24357

Supply ChainCode ExecutionFrameworkInferenceModel

vllmCWE-502945 ATLAS

Jobify WP: missing authz allows OpenAI key abuse, SSRF

CVE-2024-13698

Auth BypassDoSData ExtractionAPIPlugin

nbgrader: Clickjacking exposes formgrader via IFrame

CVE-2025-23205

Data ExtractionSocial EngineeringAuth BypassFramework

HIGHEXPLOIT AVAIL

Gradio: ACL bypass via path case manipulation

CVE-2025-23042

Auth BypassData ExtractionFrameworkAPI

gradioCWE-1787354 ATLAS

MEDIUMEXPLOIT AVAIL

Composio: command injection in AI agent tool calls

CVE-2024-53526

Code ExecutionSupply ChainFrameworkAgentAPI

composio-openaiPatch: 0.6.9CWE-7715.6K5 ATLAS

MEDIUMEXPLOIT AVAIL

Keras: path traversal enables arbitrary file write

CVE-2024-55459

Supply ChainCode ExecutionFrameworkTraining Data

kerasCWE-224.1K4 ATLAS

AIDeepin: MD5 collision enables RAG knowledge base poisoning

CVE-2025-21604

Supply ChainModel PoisoningRAGFramework

free-one-api: MD5 hashing allows credential cracking

CVE-2024-56516

Auth BypassData ExtractionAPIFramework

MEDIUMEXPLOIT AVAIL

WP Text Prompter: Stored XSS in OpenAI shortcode plugin

CVE-2024-11896

Code ExecutionData ExtractionPluginAPI

HIGHEXPLOIT AVAIL

Lobe Chat: pre-auth SSRF leaks OpenAI API keys

CVE-2024-32965

Data ExtractionAuth BypassAPIFramework

MLflow: local privilege escalation via spark_udf ToCToU

CVE-2024-27134

Code ExecutionAuth BypassFrameworkTraining Data

mlflowCWE-2766955 ATLAS

HIGHEXPLOIT AVAIL

Transformers: RCE via Trax model deserialization

CVE-2024-11394

Code ExecutionSupply ChainFrameworkModel

transformersCWE-5029.8K6 ATLAS

HIGHEXPLOIT AVAIL

Transformers: RCE via MaskFormer model deserialization

CVE-2024-11393

Code ExecutionSupply ChainFrameworkModel

transformersCWE-5029.8K6 ATLAS

HIGHEXPLOIT AVAIL

HuggingFace Transformers: RCE via config deserialization

CVE-2024-11392

Supply ChainCode ExecutionFrameworkModel

transformersCWE-5029.8K6 ATLAS

CRITICALEXPLOIT AVAIL

LlamaFactory: RCE via OS command injection in training

CVE-2024-52803

Code ExecutionSupply ChainFrameworkTraining Data

llamafactoryPatch: 0.9.1CWE-7836 ATLAS

Giskard: ReDoS in text perturbation causes DoS

CVE-2024-52524

DoSSupply ChainFramework

giskardPatch: 2.15.5CWE-13333 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