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 2876 results — no patchCVE-2026-92986SiYuan: stored XSS in backlink titles enables RCE8.80.8%—Sep 17HIGHECVE-2026-92985SiYuan: stored XSS via bookmark labels enables RCE8.80.8%—Sep 17HIGHECVE-2026-92983LMDeploy: session leak in DistServe enables DoS via OOM7.50.7%lmdeploySep 17HIGHECVE-2026-92971LMDeploy: unauthenticated assertion crash halts inference7.50.7%lmdeploySep 17HIGHCVE-2026-92925Redis: cluster bus OOB read enables DoS and info leak7.10.7%rhaii/vllm-rocm-rhel9Sep 17MEDICVE-2026-92588n8n: Source control push flaw enables cross-project deletion4.40.3%n8nSep 16MEDICVE-2026-92587n8n: Git node sandbox escape reads files outside restriction5.00.3%n8nSep 16HIGHECVE-2026-92786LightGBM: OOB write via crafted model file in SHAP7.80.2%lightgbmSep 16HIGHECVE-2026-92762Pelican Panel: missing authz lets low-priv users run commands8.80.7%—Sep 16UNKNCVE-2026-62997Kedro-Datasets: unsafe torch.load enables RCE via model—0.7%—Sep 16MEDICVE-2026-92365vLLM: algorithmic complexity DoS in thinking budget4.30.5%vllmSep 16MEDIECVE-2026-87959WPBot: missing capability check exposes Claude API key5.40.2%wpbotSep 16MEDICVE-2026-92220vLLM: MoRIIO KV handler flaw allows remote DoS5.30.7%vllmSep 16MEDICVE-2026-92298EspoCRM: weak PRNG tokens allow opt-in/invite forgery4.80.4%—Sep 16MEDICVE-2026-81926Concrete CMS: stored XSS via page path in dialog6.10.3%—Sep 15HIGHGHSA-5648-rgj9-v224mcp-gitlab: GraphQL read-only bypass, auth gaps, DoS8.1——Sep 15LOWGHSA-rf68-8gjr-36q7Nezha: Host header injection in OAuth2 redirect_uri——github.com/nezhahq/nezhaSep 15HIGHECVE-2026-18110Concrete CMS: missing authz leaks all admin accounts7.51.6%—Sep 15HIGHECVE-2026-91938Flowise: SSRF in web loaders exposes cloud metadata7.10.4%flowiseSep 15HIGHECVE-2026-91937Flowise: NoSQL injection exposes other users' chat history7.50.5%flowiseSep 15Frequently 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