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-2026-103012Claude Code: stored API key bypasses managed policy—0.1%claude-codeSep 30MEDICVE-2026-81842Grafana: incorrect authorization lets panels move across folders4.30.2%—Sep 29MEDICVE-2026-102904JupyterLab: pip option injection enables SSRF/file read5.40.2%jupyterSep 29HIGHCVE-2026-102831JupyterLab: clipboard cell-paste trust bypass enables XSS8.10.2%jupyterlite-coreSep 29MEDICVE-2026-102830JupyterLab: language pack Plural-Forms code injection6.80.3%jupyterSep 29MEDICVE-2026-102807OpenClaw: MCP app ticket bypass lets read tokens invoke write tools5.30.2%OpenClawSep 29MEDICVE-2026-102806OpenClaw: sandbox isolation bypass via media pipelines6.30.3%OpenClawSep 29HIGHCVE-2026-102697Ollama: agent Bash approval bypass via shell operators7.80.1%ollamaSep 29UNKNCVE-2026-41875Quick.Cart: CSRF in admin panel allows credential takeover—0.2%—Sep 29HIGHCVE-2026-95520rpm: heap overflow parsing crafted RPM hits RHOAI images7.1—rhoai/odh-mlflow-operator-rhel9Sep 29HIGHECVE-2026-93355LiteLLM: JWT email fallback enables admin account takeover8.10.3%litellmSep 28HIGHCVE-2026-102010GCC libstdc++: erase_if use-after-free causes DoS7.0—rhoai/odh-mlflow-operator-rhel9Sep 28MEDICVE-2026-101861Langflow: eval() code injection via component options4.10.2%langflowSep 28HIGHCVE-2026-93348Unsloth Zoo: code injection via model_type enables RCE8.10.4%—Sep 28HIGHGHSA-456v-xq2p-r4cjcode-ollama: shell injection in grep_search allows RCE7.8—ollamaSep 28MEDIECVE-2026-101011BaoTa aaPanel: SQL injection in domain status handler4.70.2%—Sep 28HIGHECVE-2026-101009aaPanel BaoTa: OS command injection in unzip handler8.41.8%—Sep 28MEDIECVE-2026-101010BaoTa Panel: SQL injection in log_type via getData4.70.2%—Sep 28CRITECVE-2026-101008aaPanel BaoTa: command injection in file merge handler9.12.3%—Sep 28HIGHECVE-2026-100846MONAI: unsafe pickle deserialization allows RCE8.80.4%monaiSep 27Frequently 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