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 2346 results — no patch CVE-2026-10129 Langflow: SSRF protection bypass via redirect 8.5 0.3% langflow Jun 30 MEDI CVE-2026-49835 Sigstore TSA: unbounded metrics label DoS 5.9 0.4% github.com/sigstore/timestamp-authority Jun 30 HIGH E CVE-2026-58116 LLaMA-Factory: RCE via malicious model path 8.8 0.9% llama-factory Jun 30 UNKN E CVE-2026-12243 NLTK: path traversal enables arbitrary file read — 0.6% — Jun 30 MEDI E CVE-2026-57948 Pinpoint: insecure JWT cookie enables session hijacking 6.8 0.2% pinpoint Jun 29 HIGH E CVE-2026-57947 Pinpoint APM: SSRF via alarm webhook registration 8.5 0.3% pinpoint Jun 29 MEDI E CVE-2026-13581 Edimax router: OS command injection via web form 6.3 2.0% — Jun 29 MEDI E CVE-2026-13561 Edimax EW-7478APC: unauth OS command injection 6.3 2.0% — Jun 29 HIGH E CVE-2026-13484 MLflow: missing authz in label schema CRUD API 8.8 0.5% — Jun 28 MEDI E CVE-2026-58057 Flowise: NODE_OPTIONS denylist bypass allows RCE 5.0 1.6% flowise Jun 28 CRIT GHSA-98x5-vq43-vc5p semantic-router: unpinned litellm dep pulls malware wheel — — litellm Jun 26 MEDI E CVE-2026-9699 Mattermost: OpenAI API key leaks into logs on auth errors 6.8 0.5% — Jun 26 HIGH E CVE-2026-57527 ZAP: insecure deserialization RCE via ViewState add-on 8.8 0.7% — Jun 26 HIGH CVE-2026-5757 Ollama: unauthenticated heap memory disclosure 7.5 0.7% Ollama Jun 26 UNKN E CVE-2026-6658 nbconvert: stored XSS via unescaped Mermaid diagrams — 0.2% — Jun 26 HIGH E CVE-2025-71340 picklescan: scanner bypass enables RCE via pickle supply chain 8.1 0.4% picklescan Jun 25 CRIT E CVE-2025-71338 Flowise: unauthenticated file write enables RCE 10.0 1.2% Flowise Jun 25 CRIT E CVE-2025-71336 Flowise: unauthenticated RCE via Custom MCP endpoint 9.8 1.1% Flowise Jun 25 HIGH E CVE-2025-71335 Flowise: password change fails to revoke sessions 8.1 0.4% Flowise Jun 25 CRIT E CVE-2025-71334 Flowise: path traversal → RCE via missing UUID validation 9.8 4.4% Flowise Jun 25 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