Résumé
npm PraisonAI SandboxExecutor allowedCommands bypass via shell chaining
Références
Vulnérabilités liées
Tout Supply chain →- HIGHGHSA-5JV7-2MJM-H6QJ
npm PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining
- HIGHGHSA-V2WW-5RH7-2H5V
OpenClaw: Linux and macOS exec allowlists skipped configured argument patterns
- HIGHGHSA-5CJ2-3JR2-5H77
OpenClaw: Shell positional parameters could weaken strict inline-eval checks
- HIGHGHSA-7QW2-W5RC-37X2
PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml
- HIGHGHSA-H2W2-V7J6-XQM4
npm PraisonAI AgentLoop onToolCall approval runs after tool execution
- CRITICALGHSA-4H5R-5JM8-JXJM
gemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)