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 2346 results — no patch CVE-2026-83551 SageMaker: HMAC leak allows forged pipeline code execution 7.2 0.4% sagemaker Sep 1 HIGH E CVE-2026-19592 Codex CLI: git core.fsmonitor hook enables RCE 7.3 0.1% Codex CLI Sep 1 CRIT CVE-2026-19593 Codex Desktop: Git config filter triggers sandbox-escape RCE 9.8 0.3% Codex Desktop Sep 1 HIGH CVE-2026-19591 Codex CLI: PowerShell parsing flaw bypasses approval, RCE 8.8 0.3% Codex CLI Sep 1 HIGH CVE-2026-19590 Codex Desktop: Git hook trust flaw enables RCE 7.3 0.1% Codex Desktop Sep 1 HIGH CVE-2026-80047 Transformers: remote file write bypasses trust prompt 7.8 0.1% transformers Sep 1 HIGH CVE-2026-5956 Ankara Site Panel: SQLi enables full DB compromise 8.8 0.2% — Aug 31 MEDI E CVE-2026-82865 pdfme: XSS via unsanitized i18n labels in Designer 4.4 0.1% — Aug 31 LOW E CVE-2026-81322 ash_cloak: encrypted field plaintext leaks into logs — 0.1% — Aug 30 HIGH E CVE-2026-82653 SiYuan: stored XSS via malicious bazaar package names 8.9 0.2% — Aug 30 MEDI E CVE-2026-82640 browser-use web-ui: stores LLM API keys in cleartext 5.5 0.1% — Aug 30 HIGH E CVE-2026-82639 NextChat: proxy URL check bypass leaks OpenAI key 7.5 0.3% — Aug 30 MEDI E CVE-2026-82637 browser-use: arbitrary directory creation via paths 5.3 0.2% browser-use Aug 30 HIGH CVE-2026-82642 Readest: iframe srcdoc XSS bypass leads to RCE 8.8 0.4% — Aug 30 MEDI E CVE-2026-75847 ash_paper_trail: sensitive fields leak in version logs — 0.1% — Aug 30 MEDI CVE-2026-82451 Formwork: stored XSS via unescaped Referer header in stats 6.1 0.2% — Aug 29 CRIT E CVE-2026-19295 Langflow: auth'd RCE bypasses custom-component block 9.9 1.8% langflow Aug 28 MEDI CVE-2026-19294 Langflow: authz flaw lets users run others' AI flows 6.5 0.2% langflow Aug 28 CRIT CVE-2026-19286 Langflow: unauthenticated RCE via A2A endpoint 9.8 0.6% langflow Aug 28 HIGH CVE-2026-18904 Langflow: namespace collision leaks data, injects messages 8.2 0.3% langflow Aug 28 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