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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 400 results — Medium severity, has patchpicklescan: scanner bypass enables RCE in ML models
GHSA-f54q-57x4-jg88 picklescan: scanner bypass enables RCE via ML models
GHSA-6vqj-c2q5-j97w picklescan: scan bypass allows RCE in ML pipelines
GHSA-x696-vm39-cp64 picklescan: scanner bypass enables RCE in ML pipelines
GHSA-g344-hcph-8vgg picklescan: bypass enables undetected RCE in ML models
GHSA-5qwp-399c-mjwf picklescan: PyTorch gadget bypasses scanner, enables RCE
GHSA-vv6j-3g6g-2pvj picklescan: PyTorch gadget bypasses pickle RCE detection
GHSA-vr7h-p6mm-wpmh picklescan: detection bypass via PyTorch proxy RCE
GHSA-h3qp-7fh3-f8h4 picklescan: RCE bypass via torch.utils.collect_env
GHSA-f745-w6jp-hpxx picklescan: scanner bypass enables RCE via PyTorch function
GHSA-f4x7-rfwp-v3xw picklescan: detection bypass enables PyTorch model RCE
GHSA-86cj-95qr-2p4f picklescan: PyTorch bypass allows undetected RCE
GHSA-4r9r-ch6f-vxmx llama-index: DocugamiReader MD5 hash collision drops chunks
CVE-2025-6211 llama-index Obsidian reader: hardlink path traversal leaks files
CVE-2025-6210 llama-index: JSONReader DoS via recursive JSON parsing
CVE-2025-5472 llama-index ArxivReader: MD5 collision corrupts training data
CVE-2025-3044 llama-index: RCE via unsafe pickle deserialization
CVE-2025-3108 MLflow: unauthenticated SSRF in gateway proxy
CVE-2025-52967 vllm: ReDoS in inference endpoints enables DoS
GHSA-j828-28rj-hfhp vLLM: DoS via unbounded XGrammar schema cache
GHSA-hf3c-wxg2-49q9 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