AI Threat AlertAI 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 4307 resultsCVE-2026-16056Contest Gallery WP: broken auth leaks OpenAI prompts4.30.3%—Aug 4HIGHECVE-2026-69249cryptography: exponential DoS in cert chain validation—0.3%cryptographyAug 3CRITECVE-2026-69085SiYuan: SQL injection in searchDocs allows DB tampering10.01.4%github.com/siyuan-note/siyuan/kernelAug 3CRITECVE-2026-69084SiYuan: SQL injection in search endpoint exposes notebooks10.01.6%github.com/siyuan-note/siyuan/kernelAug 3MEDIECVE-2026-68585SiYuan: metadata leak bypasses publish-access checks5.80.2%github.com/siyuan-note/siyuan/kernelAug 3CRITECVE-2026-69083SiYuan: unauthenticated SQLi in full-text search endpoint10.00.5%github.com/siyuan-note/siyuan/kernelAug 3HIGHCVE-2026-9856transformers: path traversal in save_pretrained() writes files7.10.5%transformersAug 2MEDICVE-2026-9335Keras: HDF5 ExternalLink flaw leaks local files on load6.50.8%kerasAug 2MEDICVE-2026-67338JupyterLab: stored XSS via malicious extension metadata6.10.3%—Aug 1CRITCVE-2026-68771ComfyUI: unauthenticated RCE via pickle upload9.81.1%—Jul 31CRITECVE-2026-68770sentence-transformers: trust gate bypass enables RCE9.80.9%sentence-transformersJul 31HIGHCVE-2026-52856Pterodactyl Wings: SFTP handshake DoS via Go panic7.50.6%—Jul 31CRITCVE-2026-52855Pterodactyl Wings: egg template leaks daemon secrets9.90.5%github.com/pterodactyl/wingsJul 31MEDICVE-2026-52857Pterodactyl Wings: config parser DoS exhausts memory5.50.2%—Jul 31MEDICVE-2026-17350pgAdmin: broken access control bypasses tool permissions5.40.4%—Jul 31HIGHGHSA-p7w7-4929-vpj5Dynatrace MCP server: unauth HTTP data exfil via DQL7.5—@dynatrace-oss/dynatrace-mcp-serverJul 31MEDIGHSA-xrmj-5g4g-8987Dynatrace MCP: Jinja injection creates persistent exfil4.2——Jul 31MEDIGHSA-pqh8-p93p-2rx7Dynatrace MCP server: DQL injection bypasses read-tool caps4.3——Jul 31MEDICVE-2026-44615Apache Zeppelin: path traversal escapes notebook root6.50.8%—Jul 31HIGHCVE-2026-14538Google mcp-toolbox: BigQuery allowedDatasets bypass7.70.2%—Jul 31Frequently 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