ClawHub
Back to skill

Security audit

Balance Checker

Security checks across malware telemetry and agentic risk

Overview

This skill coherently checks configured AI provider balances and shows no evidence of hidden exfiltration, destructive behavior, or persistence.

Install this only if you are comfortable letting the skill use the listed provider API keys to read billing balance information. Configure only providers you actually use, prefer least-privilege or billing-read-only keys where available, and review the optional Volcengine setup because it installs an unpinned Python SDK and may need minor fixing before it runs cleanly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation indicates capabilities to read environment variables, invoke shell commands, and access local files, but it does not declare permissions or present clear consent boundaries. In practice this can lead to unexpected access to sensitive API keys and execution of local setup scripts, increasing the risk of secret exposure or unintended command execution when the skill is triggered.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The documented trigger phrases are broad everyday-language requests such as '查余额' and '还有多少额度', which can plausibly appear in normal conversation unrelated to this specific skill. In an agent environment with auto-triggered skills, this can cause unintended execution that queries multiple providers and exposes financial/usage information in contexts where the user did not explicitly intend to invoke the skill.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrase "看看余额" is conversational and broad enough to match ordinary dialogue, which raises the chance of accidental activation. Because this skill uses configured credentials and makes outbound requests to third-party APIs, unintended activation can cause privacy-impacting account queries and unnecessary exposure of sensitive operational data.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill description explains how to configure provider API keys, but it does not clearly warn that the skill will read those credentials and send authenticated requests to external services. This reduces informed consent and can surprise users into exposing account metadata or incurring network activity they did not realize the skill would perform.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.