ClawHub
Back to skill

Security audit

E2B Sandbox

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently provides user-directed E2B cloud sandbox management with disclosed credential, setup, and state-file behavior.

Install this only if you want OpenClaw agents to manage E2B cloud sandboxes. Configure E2B_API_KEY securely, review the MCPorter config change before or after registration, and supervise sandbox commands, public port exposure, snapshots, and dependency installation when working with sensitive projects.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script automatically modifies the user's global mcporter configuration under the home directory and replaces or creates the e2b-sandbox entry without any prompt, backup, merge safeguards, or validation of existing settings. In a skill that provisions remote sandboxes and writes command definitions, silent config mutation is security-relevant because it can persistently change agent tool behavior and unexpectedly inject environment-backed credentials into future runs.

Static analysis

No suspicious patterns detected.