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 1961 results — Active exploitationCVE-2026-70482Open WebUI: OAuth token exchange enables takeover8.10.6%open-webuiAug 4MEDIECVE-2026-70481Open WebUI: members can edit/delete others' channel messages5.40.4%open-webuiAug 4HIGHECVE-2026-70479Open WebUI: Playwright SSRF leaks cloud metadata7.70.5%open-webuiAug 4CRITECVE-2026-70478Flowise: unauth OAuth refresh endpoint leaks access tokens—0.6%flowiseAug 4UNKNECVE-2026-70477Flowise: prompt injection bypasses sandbox for RCE—0.8%flowise-componentsAug 4UNKNECVE-2026-70476Flowise: billing IDOR lets tenants hijack Stripe subs—0.5%flowiseAug 4UNKNECVE-2026-70475Flowise: missing authz lets users tamper executions—0.5%flowiseAug 4HIGHECVE-2026-70474Flowise: missing workspace auth in OAuth2 credential routes—0.5%flowiseAug 4UNKNECVE-2026-70473Flowise: broken authz leaks Qdrant config, infra data—0.5%flowiseAug 4HIGHECVE-2026-70472Flowise: broken auth exposes cross-tenant OpenAI keys—0.5%flowiseAug 4UNKNECVE-2026-70470Flowise: Unicode homoglyph bypass enables RCE—1.0%FlowiseAug 4UNKNECVE-2026-69264Flowise: CSV Agent template injection enables host RCE—1.1%FlowiseAug 4UNKNECVE-2026-69263Flowise: env-var bypass reinstates npx auto-exec RCE—0.7%flowise-componentsAug 4HIGHECVE-2026-69262Flowise: broken authz allows cross-type flow deletion—0.5%flowiseAug 4UNKNECVE-2026-69259Flowise: RCE via SQLite path overwrite + root Docker—0.8%flowise-componentsAug 4HIGHECVE-2026-69258Flowise: unauth overrideConfig injects flow session state—0.7%flowiseAug 4UNKNECVE-2026-69255Flowise: code injection in CSVAgent enables root RCE—0.6%flowise-componentsAug 4UNKNECVE-2026-69254Flowise: authenticated RCE as root via NodeVM sandbox escape—0.7%flowise-componentsAug 4CRITECVE-2026-69253Flowise: code injection in agent tools escapes vm2 sandbox—0.7%flowise-componentsAug 4UNKNECVE-2026-69252Flowise: missing authz allows cross-workspace file wipe—0.5%flowiseAug 4Frequently 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