ClawHub
Back to skill

Security audit

人身损害赔偿计算

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local calculator for Chinese personal-injury compensation, with disclosed script use and optional user-directed exports.

Install only if you are comfortable running a local legal-compensation calculator on sensitive case details. Save exported Markdown, JSON, or XLSX files only in locations appropriate for confidential legal or medical records, and verify any externally researched statistics before relying on the result.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to read local reference files and write output files such as Markdown, JSON, and XLSX, but the metadata shown in this file does not declare corresponding permissions. Undeclared file read/write capability weakens policy enforcement and user visibility, increasing the chance of unauthorized local data access or unintended file creation/overwrite if the skill is invoked in a broader agent environment.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.