ClawHub
Back to skill

Security audit

employee-handover

Security checks across malware telemetry and agentic risk

Overview

This skill handles sensitive employee handover data, but its access and outputs are disclosed, scoped, and aligned with that purpose.

Before installing, make sure users only provide chat logs, employee details, and file paths they are authorized to use, define the time and participant scope up front, and confirm who may receive the final handover file. Treat generated spreadsheets and intermediate files as sensitive HR/workplace records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The manifest description and the entire skill instructions are written as mandatory Chinese-language operating guidance, including fixed Chinese output structures, without indicating that users may choose another language. This can violate language/locale policy where skills must not force a specific language absent user opt-in or a documented regional justification.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.