AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 512 results — has patchlanggraph-checkpoint-sqlite: SQL Injection exposes database
CVE-2025-8709 keras: Deserialization enables RCE
CVE-2025-49655 llama-index: world-writable NLTK dir allows local tampering
CVE-2025-7707 vllm: DoS via Jinja template injection in chat API
CVE-2025-61620 vLLM: SSRF in media loader exposes internal network
CVE-2025-6242 LLaMA-Factory: SSRF+LFI in multimodal chat API
CVE-2025-61784 langchain-text-splitters: XXE enables arbitrary file read
CVE-2025-6985 clearml: path traversal in safe_extract → RCE risk
CVE-2025-8917 llama-index-core: insecure /tmp dir, model theft risk
CVE-2025-7647 Picklescan: CRC bypass hides malicious pickle in ZIP
CVE-2025-10156 PickleScan: subclass bypass enables malicious model RCE
CVE-2025-10157 MONAI: unsafe pickle deserialization RCE in data pipeline
CVE-2025-58757 MONAI: unsafe deserialization in CheckpointLoader allows RCE
CVE-2025-58756 MONAI: path traversal allows arbitrary file write
CVE-2025-58755 xgrammar: DoS via oversized JSON schema grammar parsing
CVE-2025-58446 EverNoteLoader: XXE exposes host files in LangChain
CVE-2025-6984 picklescan: scanner bypass enables model RCE
GHSA-q77w-mwjj-7mqx picklescan: scanner bypass enables RCE via ML model files
GHSA-49gj-c84q-6qm9 picklescan: scan bypass allows silent RCE via ML models
GHSA-9w88-8rmg-7g2p picklescan: detection bypass allows undetected RCE in ML models
GHSA-fqq6-7vqf-w3fg 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
AI Threat Alert