Back to skill

Security audit

Ai Intelligent Attendance Management

Security checks across malware telemetry and agentic risk

Overview

This appears to be a simple attendance-management skill description, with caution needed before running its unreviewed external GitHub app or handling employee data.

Before installing, inspect the linked GitHub repository and Python dependencies because they were not included in this review. Use the skill only with proper HR authorization, access controls, audit logging, retention limits, and care around attendance, leave, and payroll-related employee data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The manifest description is inconsistent with the stated purpose of the skill, which is attendance management for clock-ins, leave, and statistics. A mismatched description can cause users or orchestration systems to misunderstand when the skill should be invoked, increasing the chance of overbroad activation or misuse in unrelated contexts.

Vague Triggers

Low
Confidence
89% confidence
Finding
The description 'AI intelligent ai-intelligent-attendance-management' is too vague and generic to establish a narrow operational scope. Overly broad metadata can lead to ambiguous routing, accidental invocation, or user confusion about the skill's intended capabilities, which is especially undesirable for HR-related workflows involving employee data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.