ClawHub
Back to skill

Security audit

Tmp.2QyoIdCVJh

Security checks across malware telemetry and agentic risk

Overview

This skill clearly documents read-only access to a user's own Workday HR data, with sensitive-session use disclosed and no artifact evidence of hidden or destructive behavior.

Install only if you are comfortable letting an MCP server read sensitive Workday information through your active browser session. Confirm the package and fetchproxy extension source, use it only for your own account, and check your employer's acceptable-use rules before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger text includes a broad catch-all phrase: 'any request involving your Workday tasks, pay, or benefits.' This can cause over-activation on loosely related prompts and unnecessarily route sensitive HR requests to this skill, increasing the chance of unintended data access or disclosure of compensation, benefits, or task information.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal