AI Threat Alert
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 14 of 15
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| MEDIUM | GHSA-h2v7-xc88-xx8c | openclaw: operator scope bypass in phone arm/disarm cmds | openclaw | - |
| MEDIUM | CVE-2026-39398 | openclaw-claude-bridge: sandbox bypass exposes CLI tools | claude-code | - |
| MEDIUM | GHSA-766v-q9x3-g744 | praisonaiagents: agent context leak + path traversal | praisonaiagents | 6.5 |
| HIGH | CVE-2026-39891 | praisonai: SSTI enables RCE via agent instructions | praisonai | 8.8 |
| HIGH | CVE-2026-39889 | PraisonAI: unauth A2U stream leaks all agent activity | praisonai | 7.5 |
| CRITICAL | CVE-2026-39888 | praisonaiagents: sandbox escape enables host RCE | praisonaiagents | 10.0 |
| CRITICAL | CVE-2026-39890 | PraisonAI: YAML deserialization enables unauthenticated RCE | praisonai | 9.8 |
| HIGH | GHSA-4ggg-h7ph-26qr | n8n-mcp: authenticated SSRF leaks cloud metadata | n8n-mcp | 8.5 |
| CRITICAL | GHSA-2763-cj5r-c79m | PraisonAI: RCE via shell injection in agent workflows | PraisonAI | 9.7 |
| MEDIUM | CVE-2026-1163 | lollms: sessions persist after password reset | lollms | 4.1 |
| HIGH | GHSA-7437-7hg8-frrw | OpenClaw: env var injection enables host RCE | openclaw | - |
| HIGH | GHSA-jf56-mccx-5f3f | OpenClaw: wake hook trust violation elevates to System prompt | openclaw | - |
| HIGH | GHSA-gfmx-pph7-g46x | openclaw: trust boundary bypass enables prompt injection | openclaw | - |
| HIGH | CVE-2026-39974 | n8n-MCP: SSRF exposes cloud metadata via MCP headers | 8.5 | |
| MEDIUM | GHSA-ccx3-fw7q-rr2r | openclaw: base64 pre-alloc bypass causes resource exhaustion | openclaw | - |
| MEDIUM | GHSA-3vvq-q2qc-7rmp | openclaw: no integrity check on ClawHub plugin installs | openclaw | - |
| HIGH | GHSA-qx8j-g322-qj6m | OpenClaw: unsafe body replay on cross-origin redirect | openclaw | - |
| MEDIUM | GHSA-w9j9-w4cp-6wgr | openclaw: env var injection enables host exec hijacking | openclaw | - |
| MEDIUM | GHSA-w8g9-x8gx-crmm | OpenClaw: SSRF bypass via Playwright redirect handling | openclaw | - |
| LOW | GHSA-4f8g-77mw-3rxc | OpenClaw: gateway auth expands read to write privilege | openclaw | - |