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-6pcv-j4jx-m4vxFlowise: unauthenticated SSO config exposes OAuth secrets5.3—flowiseApr 16MEDIECVE-2026-40190langsmith: prototype pollution enables auth bypass, RCE5.60.3%langsmithApr 10MEDIECVE-2026-40086rembg: path traversal exposes arbitrary files via HTTP API5.30.6%rembgApr 10MEDIGHSA-x783-xp3g-mqhpPraisonAI: SQL injection via table_prefix exposes DB——PraisonAIApr 10MEDIGHSA-ffp3-3562-8cv3PraisonAI: tool approval bypass leaks env credentials5.5—praisonaiagentsApr 10MEDIECVE-2026-40159PraisonAI: MCP env inheritance exposes API keys5.50.2%PraisonAIApr 10MEDIECVE-2026-40148PraisonAI: decompression bomb causes disk exhaustion6.50.2%PraisonAIApr 10MEDIECVE-2026-40152praisonaiagents: glob traversal leaks filesystem metadata5.30.4%praisonaiagentsApr 10MEDIECVE-2026-40151PraisonAI: unauthenticated agent config and system prompt disclosure5.30.8%PraisonAIApr 10MEDIECVE-2026-40115PraisonAI: unbounded body read enables local DoS6.20.3%PraisonAIApr 10MEDICVE-2026-35651OpenClaw: ANSI injection spoof AI agent approval prompts4.30.3%openclawApr 10MEDICVE-2026-35670OpenClaw: webhook rebinding exposes user data5.90.2%OpenClawApr 10MEDIECVE-2026-35667OpenClaw: SIGKILL bypass skips security-sensitive cleanup6.10.1%OpenClawApr 10MEDIECVE-2026-35665OpenClaw: pre-auth resource exhaustion via Feishu webhook DoS5.30.3%OpenClawApr 10MEDICVE-2026-35664OpenClaw: auth bypass enables unauthorized callback injection5.30.3%OpenClawApr 10MEDICVE-2026-35662OpenClaw: missing auth enables agent scope bypass4.30.2%OpenClawApr 10MEDICVE-2026-35661OpenClaw: auth bypass mutates AI agent session state5.30.3%OpenClawApr 10MEDICVE-2026-35659OpenClaw: DNS-SD metadata hijacks CLI routing4.60.1%OpenClawApr 10MEDICVE-2026-35658OpenClaw: sandbox bypass exposes host filesystem reads6.50.3%OpenClawApr 10MEDICVE-2026-35656OpenClaw: auth bypass via X-Forwarded-For spoofing6.50.3%OpenClawApr 10Frequently 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