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 1527 results — Medium severityGHSA-gr75-jv2w-4656LangChain: path traversal exposes files outside sandbox5.1—langchain-anthropicJun 16MEDIGHSA-534h-c3cw-v3h9Nuxt: local unauth IPC leaks .env secrets on shared hosts5.5—nuxtJun 16MEDIGHSA-c9cv-mq2m-ppp3Nuxt: open redirect + XSS in navigation API (SSR+client)6.10.4%nuxtJun 16MEDICVE-2026-53839OpenClaw: hostname prefix bypass leaks auth tokens6.50.3%OpenClawJun 12MEDICVE-2026-53835OpenClaw: auth bypass in Feishu agent binding controls4.30.2%OpenClawJun 12MEDICVE-2026-53830OpenClaw: stale webhook secrets bypass revocation6.50.2%OpenClawJun 12MEDICVE-2026-53827OpenClaw: SSRF leaks Gateway credentials via model metadata6.50.3%OpenClawJun 12MEDICVE-2026-53826OpenClaw: workspace path leaked from sandboxed sessions4.30.2%OpenClawJun 12MEDICVE-2026-53825OpenClaw: path traversal exposes local files via wiki ingest6.50.4%OpenClawJun 12MEDICVE-2026-53824OpenClaw: stale slash tokens bypass revocation controls6.50.2%OpenClawJun 12MEDICVE-2026-53820OpenClaw: exec denylist bypass via MCP session-spawn6.60.1%OpenClawJun 12MEDICVE-2026-47345typo3/html-sanitizer: XSS bypass via namespace encoding—0.5%typo3/html-sanitizerJun 12MEDIECVE-2026-48148Budibase: SSRF via VectorDB host exposes cloud metadata—0.2%@budibase/serverJun 12MEDICVE-2026-48121LangGraph MongoDB: NoSQL injection leaks tenant checkpoints6.70.4%@langchain/langgraph-checkpoint-mongodbJun 12MEDICVE-2026-50634Apache CXF: JWS signature bypass exposes JAX-RS APIs6.50.3%org.apache.cxf:cxf-rt-rs-security-jose-jaxrsJun 12MEDICVE-2026-53818OpenClaw: MCP loopback auth bypass enables policy evasion6.60.1%openclawJun 11MEDICVE-2026-53815OpenClaw: auth bypass exposes restricted channel messages6.50.2%openclawJun 11MEDICVE-2026-53808OpenClaw: approval bypass enables unauthorized skill changes6.50.2%OpenClawJun 11MEDICVE-2026-3341Langflow: SSRF exposes internal ML infrastructure5.40.1%langflowJun 11MEDICVE-2026-11850krb5: integer underflow in LDAP KDB causes heap over-read5.0—rhoai/odh-mlflow-operator-rhel9Jun 11Frequently 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