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 4307 resultsCVE-2026-18899Langflow: path traversal enables arbitrary file read7.50.7%langflowAug 28HIGHCVE-2026-18891Langflow: broken auth allows unauthorized flow execution8.20.5%langflowAug 28HIGHECVE-2026-18729Langflow: authenticated RCE via unsafe code generation8.81.6%langflowAug 28MEDICVE-2026-18545Langflow: SSRF lets authenticated users probe internal network4.30.3%langflowAug 28MEDIECVE-2026-82290Chainlit: IDOR lets users tamper with others' feedback5.30.3%chainlitAug 28HIGHECVE-2026-82288SD WebUI: cmd-flags endpoint leaks creds cleartext7.50.4%—Aug 28HIGHECVE-2026-82275Qwen-Agent: path traversal in doc parser leaks files7.50.5%—Aug 28HIGHECVE-2026-82268Qwen-Agent: unauth SSRF via document URL parser7.50.5%—Aug 28CRITECVE-2026-55634Pimcore: DataObject field-name injection → RCE9.90.7%pimcore/pimcoreAug 28CRITECVE-2026-55220Pimcore: PHP deserialization flaw enables RCE—0.7%pimcore/pimcoreAug 28HIGHECVE-2026-556419router: Host-header spoof bypasses auth, enables SSRF8.20.3%9routerAug 28HIGHECVE-2026-556389router: /codex bypass exposes LLM proxy credentials8.66.6%9routerAug 28HIGHCVE-2026-37237vLLM: unbounded media URLs cause memory-exhaustion DoS7.50.7%vllmAug 28MEDICVE-2026-82327libsolv: OOB write in .solv cache causes tool crash5.5—rhoai/odh-mlflow-operator-rhel9Aug 28MEDICVE-2026-18393FFmpeg: heap overflow via crafted TDSC cursor in video5.40.4%rhoai/odh-vllm-gaudi-rhel9Aug 28LOWECVE-2026-81836Roo-Code: cleartext OAuth callback leaks auth tokens3.70.3%—Aug 27MEDIECVE-2026-37009crewai-tools: SQLi in NL2SQLTool allows DB compromise6.50.4%—Aug 27CRITECVE-2026-37007crewai-tools: Path traversal in FileWriterTool enables RCE9.81.0%—Aug 27CRITECVE-2026-37004LiteLLM: unauth SSTI in /prompts/test enables RCE9.80.8%litellmAug 27MEDICVE-2026-54687n8n-nodes-sqlite3: path traversal via db_path—0.8%n8n-nodes-sqlite3Aug 27Frequently 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