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 1051 results — Medium severity CVE-2026-55646 vLLM: audio upload OOMs process before size check 6.5 0.3% vllm Jul 6 MEDI CVE-2026-14898 OpenAI Codex: prompt injection exfils data via images 6.5 0.3% — Jul 6 MEDI CVE-2026-40257 OP-TEE: off-by-one in SHA-3 CE overflows TEE kernel heap 5.5 0.1% — Jul 6 MEDI CVE-2026-59152 LangSmith SDK: arbitrary file read via TracingMiddleware 5.0 0.2% langsmith-sdk Jul 6 MEDI E CVE-2026-14647 ONNX: OOB read in shape inference parsing untrusted models 4.3 0.3% onnx Jul 4 MEDI CVE-2026-9557 Mautic Focus: SSRF enables internal network recon 6.4 0.1% mautic/core Jul 2 MEDI GHSA-4m3v-q747-pc6h OpenClaw: slash token revocation lag allows reuse — — openclaw Jul 2 MEDI GHSA-275c-xpvc-jgfw OpenClaw: Slack/Zalo webhook secrets outlive rotation — — openclaw Jul 2 MEDI GHSA-6c4r-g249-wv3c OpenClaw: sandbox leaks host workspace path to child — — openclaw Jul 2 MEDI GHSA-77pv-3w4q-vrj5 OpenClaw: QQBot slash commands bypass allowFrom auth — — openclaw Jul 2 MEDI GHSA-hcm3-8f6r-6xwg OpenClaw: missing authz reuses blocked SSRF tabs 6.5 — openclaw Jul 2 MEDI GHSA-grc3-2j34-p6gm OpenClaw: action forwarding leaks Gateway credentials — — openclaw Jul 2 MEDI GHSA-gp79-m99v-gjmh OpenClaw: fail-open bypasses Mattermost DM channel policy — — openclaw Jul 2 MEDI GHSA-cqwv-9qjx-vxw2 OpenClaw: agent tool call bypasses skill approval gate 5.3 — openclaw Jul 2 MEDI GHSA-wv26-j37q-2g7p OpenClaw: exec approver can bypass plugin approval gate — — openclaw Jul 2 MEDI GHSA-p2fh-f5fc-44hr OpenClaw: memory-wiki ingest reads arbitrary local files 6.5 — openclaw Jul 2 MEDI GHSA-qh2f-99mv-mrcf OpenClaw: exec denylist bypass in bundled MCP loopback — — openclaw Jul 2 MEDI E CVE-2026-58653 PraisonAI: IDOR cross-tenant data pollution 4.3 0.2% praisonai Jul 2 MEDI CVE-2026-50280 Craft CMS: entry section permission bypass — 0.3% — Jul 1 MEDI GHSA-9c3v-684m-579c OpenClaw: MCP SSE redirect leaks Authorization headers 6.5 — openclaw Jul 1 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