ClawHub
Back to skill

Security audit

诉讼费计算

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed litigation-fee calculator that uses an external DeliLegal CLI/backend, with a credential-handling caution but no evidence of hidden or malicious behavior.

Use this skill only if you trust the DeliLegal CLI/backend with the legal facts you provide. Treat the API key as a secret, avoid entering it in shared terminals, and rotate it if it may have been exposed.

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 document instructs users to pass an API key directly on the command line and discloses the local config storage path, but does not warn that command-line arguments may be exposed through shell history, process listings, logs, or shared terminals. In a legal-services CLI context, such credentials could grant access to backend services or user-associated data, so normalizing this workflow without handling guidance creates a real secret-exposure risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.