ClawHub
Back to skill

Security audit

Sandbox Manager

Security checks across malware telemetry and agentic risk

Overview

The skill does what it claims, but it handles sandbox credentials too loosely for automatic installation without review.

Install only if you trust the Baidu sandbox service and package index. Do not let the skill write secrets to ~/.env without reviewing the change; prefer a session-only environment variable or a dedicated credential file with restricted permissions. Avoid sharing sandbox URLs, confirm command execution and sandbox deletion explicitly, and rotate the API key if any part of it appears in logs or screenshots.

SkillSpector

By NVIDIA
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
94% confidence
Finding
The script prints the first 10 characters of the API key to the console during configuration checks. Even partial secret disclosure can aid credential correlation, leak into terminal history/CI logs, and reduce the effort needed for an attacker who already has partial access to logs or output streams.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.