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 1961 results — Active exploitationCVE-2026-68586SiYuan: missing authz leaks forbidden doc content via backlink API8.60.4%github.com/siyuan-note/siyuan/kernelSep 3HIGHECVE-2026-68587SiYuan: missing authz exposes publish-disabled docs8.60.3%github.com/siyuan-note/siyuan/kernelSep 3UNKNECVE-2026-85063csv-parse: CSV header triggers prototype pollution—0.6%—Sep 3HIGHECVE-2026-69086SiYuan: path traversal leaks attribute-view data7.70.5%github.com/siyuan-note/siyuan/kernelSep 3CRITECVE-2026-71428unstructured: SSRF via url= param exposes internal APIs9.30.4%unstructuredSep 3HIGHECVE-2026-85180Ollama: SSRF via unvalidated model-pull redirects7.50.5%ollamaSep 3HIGHECVE-2026-85178Helicone: IDOR leaks cross-tenant LLM provider keys7.70.4%—Sep 3MEDIECVE-2026-73846ckan-mcp-server: cache key collision enables poisoning6.50.2%—Sep 3HIGHECVE-2026-85211Label Studio: org filter bypass leaks tenant storage7.70.4%label-studioSep 3HIGHECVE-2026-85179Label Studio: SSRF via webhooks hits cloud metadata8.50.4%label-studioSep 3HIGHECVE-2026-84801Craft CMS: auth bypass enables admin takeover8.80.4%—Sep 2HIGHECVE-2026-19592Codex CLI: git core.fsmonitor hook enables RCE7.30.2%Codex CLISep 1HIGHECVE-2026-80047Transformers: remote file write bypasses trust prompt7.80.1%transformersSep 1MEDIECVE-2026-82865pdfme: XSS via unsanitized i18n labels in Designer4.40.2%—Aug 31LOWECVE-2026-81322ash_cloak: encrypted field plaintext leaks into logs—0.1%—Aug 30HIGHECVE-2026-82653SiYuan: stored XSS via malicious bazaar package names8.90.4%—Aug 30MEDIECVE-2026-82640browser-use web-ui: stores LLM API keys in cleartext5.50.1%—Aug 30HIGHECVE-2026-82639NextChat: proxy URL check bypass leaks OpenAI key7.50.5%—Aug 30MEDIECVE-2026-82637browser-use: arbitrary directory creation via paths5.30.4%browser-useAug 30MEDIECVE-2026-75847ash_paper_trail: sensitive fields leak in version logs—0.1%—Aug 30Frequently 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