AI Threat Alert
Attack Type
Data Extraction
Data extraction attacks target AI/ML systems to exfiltrate training data, model weights, user conversations, or other sensitive information. These vulnerabilities are critical in multi-tenant AI deployments.
413
Total CVEs
21
Pages
Page 17 of 21
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| CRITICAL | CVE-2023-32785 | LangChain: prompt injection → SQL RCE (CVSS 9.8) | langchain | 9.8 |
| MEDIUM | CVE-2024-6985 | lollms: path traversal allows arbitrary directory read | lollms | 4.4 |
| LOW | CVE-2024-6971 | lollms: path traversal in RAG database functions | lollms | 3.4 |
| LOW | CVE-2024-7038 | open-webui: filesystem enumeration via admin error messages | open-webui | 2.7 |
| HIGH | CVE-2021-41134 | nbdime: stored XSS in Jupyter notebook diff viewer | 8.7 | |
| MEDIUM | CVE-2022-36551 | Label Studio: SSRF + file read, self-reg bypass | label-studio | 6.5 |
| HIGH | CVE-2018-8768 | Jupyter Notebook: XSS via malicious .ipynb file | notebook | 7.8 |
| HIGH | CVE-2025-15381 | MLflow: broken access control exposes experiment traces | mlflow | 8.1 |
| UNKNOWN | CVE-2026-34046 | Langflow: IDOR exposes flows and plaintext API keys | langflow | - |
| MEDIUM | CVE-2026-27496 | n8n: uninitialized buffer leaks secrets via Task Runner | n8n | 6.5 |
| CRITICAL | CVE-2026-33663 | n8n: member role steals plaintext HTTP credentials | n8n | 10.0 |
| HIGH | CVE-2026-33665 | n8n: LDAP email match enables permanent account takeover | n8n | 8.2 |
| HIGH | CVE-2026-33713 | n8n: SQLi in Data Table node, full DB compromise | n8n | 8.8 |
| MEDIUM | CVE-2026-33720 | n8n: OAuth state forgery hijacks user credentials | n8n | 4.2 |
| MEDIUM | CVE-2026-33722 | n8n: secrets vault bypass exposes credentials to low-priv users | n8n | 5.3 |
| CRITICAL | CVE-2026-33749 | n8n: stored XSS enables credential theft via workflow | n8n | 9.0 |
| MEDIUM | CVE-2026-33751 | n8n: LDAP injection enables auth bypass in workflows | n8n | 4.8 |
| HIGH | CVE-2026-34070 | langchain-core: path traversal exposes host secrets via prompt config | langchain-core | 7.5 |
| LOW | CVE-2026-29071 | Open WebUI: IDOR exposes AI memories and private files | open-webui | 3.1 |
| MEDIUM | CVE-2026-28786 | Open WebUI: path traversal leaks server filesystem path | open-webui | 4.3 |