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 1050 results — Medium severity CVE-2026-65596 n8n: GraphQL node bypasses domain allowlist, leaks creds — 0.2% n8n Jul 22 MEDI CVE-2026-65594 n8n: authz bypass hijacks other users' MCP workflows — 0.3% n8n Jul 22 MEDI CVE-2026-65593 n8n: SSRF bypass in dynamic-node-parameters endpoint — 0.1% n8n Jul 22 MEDI CVE-2026-65590 n8n computer-use: unsandboxed shell on Linux/Windows — 0.3% n8n Jul 22 MEDI CVE-2026-65589 n8n: plaintext credential leak in LLM node logs — 0.4% n8n Jul 22 MEDI CVE-2026-65014 n8n: unauth DELETE cancels test webhook sessions — 0.3% n8n Jul 22 MEDI CVE-2026-60152 PeopleSoft: unauthorized data access via Panel Processor 5.4 0.2% — Jul 21 MEDI CVE-2026-47024 PeopleSoft PeopleTools: CSRF-style data tampering flaw 5.4 0.2% — Jul 21 MEDI CVE-2026-63092 Kirby Modules: license key disclosure via activate dialog 4.3 0.2% — Jul 21 MEDI CVE-2026-58435 Gitea: LFS deploy-key flaw leaks private repo objects 5.4 — code.gitea.io/gitea Jul 21 MEDI E CVE-2026-14185 WPBot: missing auth check lets subscribers edit RAG config 4.3 0.2% — Jul 21 MEDI CVE-2026-64650 @ai-sdk/harness-codex: tool relay authz bypass — 0.1% — Jul 20 MEDI CVE-2026-46671 onenote_parser: path traversal via crafted .onetoc2 file 4.4 0.1% — Jul 20 MEDI CVE-2026-7754 Langflow: SSRF via incomplete protection bypass 6.5 0.2% langflow Jul 17 MEDI CVE-2026-62225 OpenClaw: authz bypass in skill dispatch 5.4 0.1% openclaw Jul 17 MEDI CVE-2026-62224 OpenClaw: MS Teams auth bypass via display name spoof 5.4 0.2% openclaw Jul 17 MEDI CVE-2026-62221 OpenClaw: allowFrom auth bypass runs blocked commands 5.4 0.1% openclaw Jul 17 MEDI CVE-2026-62220 OpenClaw: WS auth rate-limit bypass enables DoS 5.3 0.3% openclaw Jul 17 MEDI CVE-2026-62216 OpenClaw: policy bypass enables SSRF via media upload 5.0 0.2% openclaw Jul 17 MEDI CVE-2026-62214 OpenClaw: serviceUrl validation flaw leaks bot tokens 6.5 0.3% openclaw Jul 17 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