AI Component
Agent
AI agent frameworks (AutoGPT, CrewAI, LangGraph, etc.) orchestrate LLM-powered autonomous actions. Their tool-use capabilities create unique attack surfaces not present in simple chat interfaces.
300
Total CVEs
15
Pages
Page 10 of 15
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| MEDIUM | CVE-2024-53526 | Composio: command injection in AI agent tool calls | 6.4 | |
| 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 |
| MEDIUM | CVE-2024-7041 | open-webui: IDOR enables cross-user memory tampering | open-webui | 6.5 |
| MEDIUM | CVE-2026-4963 | smolagents: code injection via incomplete sandbox fix | 6.3 | |
| UNKNOWN | CVE-2026-33873 | Langflow: server-side RCE via LLM-generated code exec | langflow | - |
| 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-2026-33696 | n8n: Prototype pollution enables RCE via workflow nodes | n8n | 8.8 |
| 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 |
| HIGH | CVE-2026-33724 | n8n: SSH MitM enables malicious workflow injection | n8n | 7.4 |
| 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 |
| LOW | CVE-2026-29071 | Open WebUI: IDOR exposes AI memories and private files | open-webui | 3.1 |
| CRITICAL | GHSA-5mg7-485q-xm76 | litellm: supply chain attack harvests AI API credentials | litellm | - |
AI Threat Alert