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 512 results — has patch
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2025-8709 langgraph-checkpoint-sqlite: SQL Injection exposes database 7.3 0.0% langgraph-checkpoint-sqlite Oct 26 CRIT E CVE-2025-49655 keras: Deserialization enables RCE 9.8 0.1% keras Oct 17 HIGH CVE-2025-7707 llama-index: world-writable NLTK dir allows local tampering 7.1 0.0% llama-index Oct 13 MEDI CVE-2025-61620 vllm: DoS via Jinja template injection in chat API 6.5 — vllm Oct 7 HIGH E CVE-2025-6242 vLLM: SSRF in media loader exposes internal network 7.1 0.1% vllm Oct 7 HIGH E CVE-2025-61784 LLaMA-Factory: SSRF+LFI in multimodal chat API 8.1 0.1% llamafactory Oct 7 HIGH E CVE-2025-6985 langchain-text-splitters: XXE enables arbitrary file read 7.5 0.2% langchain-text-splitters Oct 6 MEDI E CVE-2025-8917 clearml: path traversal in safe_extract → RCE risk 5.8 0.0% clearml Oct 5 HIGH E CVE-2025-7647 llama-index-core: insecure /tmp dir, model theft risk 7.3 0.0% llama-index-core Sep 27 HIGH E CVE-2025-10156 Picklescan: CRC bypass hides malicious pickle in ZIP 7.5 1.0% picklescan Sep 10 HIGH E CVE-2025-10157 PickleScan: subclass bypass enables malicious model RCE 8.3 0.2% picklescan Sep 10 HIGH E CVE-2025-58757 MONAI: unsafe pickle deserialization RCE in data pipeline 8.8 0.8% monai Sep 9 HIGH E CVE-2025-58756 MONAI: unsafe deserialization in CheckpointLoader allows RCE 8.8 1.7% monai Sep 9 HIGH E CVE-2025-58755 MONAI: path traversal allows arbitrary file write 8.8 0.1% monai Sep 9 MEDI E CVE-2025-58446 xgrammar: DoS via oversized JSON schema grammar parsing — 0.1% xgrammar Sep 5 HIGH E CVE-2025-6984 EverNoteLoader: XXE exposes host files in LangChain 7.5 1.9% langchain-community Sep 4 MEDI GHSA-q77w-mwjj-7mqx picklescan: scanner bypass enables model RCE — — picklescan Aug 26 MEDI GHSA-49gj-c84q-6qm9 picklescan: scanner bypass enables RCE via ML model files — — picklescan Aug 26 MEDI GHSA-9w88-8rmg-7g2p picklescan: scan bypass allows silent RCE via ML models — — picklescan Aug 26 MEDI GHSA-fqq6-7vqf-w3fg picklescan: detection bypass allows undetected RCE in ML models — — picklescan Aug 26

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