中小团队HR自动化工具包

Security checks across malware telemetry and agentic risk

Overview

This is a static HR document-template skill with expected personal-data fields and no evidence of hidden execution, persistence, or exfiltration.

Use this as a drafting aid only. Before entering real employee data such as national ID numbers, addresses, phone numbers, or salary, confirm you are authorized to process it, enter only what is necessary, and store generated documents in approved secure channels. Separately review any referenced dependency skill before relying on it.

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)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: This skill asks users to process highly sensitive HR and identity data, including names, salary, employment dates, and national ID numbers, but does not provide any warning or handling guidance for personal data protection. In an HR context, this omission is more dangerous because users may paste regulated employee data into an AI workflow without understanding retention, disclosure, or minimization risks, potentially causing privacy breaches or compliance violations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal