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 1908 results — High severityCVE-2026-61647NotebookLM MCP: path traversal enables arbitrary file write—0.4%@roomi-fields/notebooklm-mcpSep 21HIGHCVE-2026-55105Joplin: stored XSS via Fountain renderer exposes notes7.70.5%—Sep 21HIGHECVE-2026-49453Joplin: path traversal in sync allows arbitrary file write7.00.4%—Sep 21HIGHECVE-2026-49450Joplin Desktop: update signature check skipped on Windows7.10.2%—Sep 21HIGHCVE-2026-36467CuteNews: authenticated file upload leads to RCE7.20.5%—Sep 21HIGHECVE-2026-93993Mistral Vibe: RCE via git hooks run before trust check8.80.8%mistral-vibeSep 19HIGHECVE-2026-93923SiYuan: stored XSS in heading style enables Electron RCE8.80.6%—Sep 18HIGHECVE-2026-93922SiYuan: stored XSS in notebook names enables RCE8.80.8%—Sep 18HIGHECVE-2026-58197ToolHive: default network profile enables MCP lateral movement8.80.4%github.com/stacklok/toolhiveSep 18HIGHGHSA-39wr-7q6h-cf68lmdeploy: URL parser mismatch enables SSRF bypass7.5—lmdeploySep 18HIGHECVE-2026-33625LMDeploy: eval() injection via malicious model config8.80.4%lmdeploySep 18HIGHECVE-2026-93592vLLM: negative token ID crashes embeddings engine7.50.5%vllmSep 18HIGHECVE-2026-93591SiYuan: SQL injection in getGraph exposes private notes7.60.3%—Sep 18HIGHCVE-2026-93436vLLM: memory leak in PD disaggregation causes DoS7.50.8%vllmSep 17HIGHECVE-2026-54507Vvveb CMS: SSRF in oEmbed proxy leaks cloud metadata—0.4%—Sep 17HIGHECVE-2026-86049Jupyter Server: Referer token leak in 5xx logs7.10.4%jupyterSep 17HIGHCVE-2026-76154Grafana Geomap: stored XSS enables Org Admin escalation7.30.4%—Sep 17HIGHECVE-2026-72819Grav CMS: callable-array bypass enables authenticated RCE8.80.9%getgrav/gravSep 17HIGHECVE-2026-69088Grav CMS: callable guard bypass enables file read/write8.10.3%getgrav/gravSep 17HIGHCVE-2026-77407amqp091-go: cleartext AMQP password retained in memory—0.1%github.com/rabbitmq/amqp091-goSep 17Frequently 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