ClawHub

client-flow

Security checks across malware telemetry and agentic risk

Overview

This skill matches its client-onboarding purpose, but it needs review because one prompt can modify several business tools and persist client data without clear approval and retention boundaries.

Install only if you want an agent to coordinate real client onboarding across your connected business tools. Before using it, confirm the exact email, calendar, storage, and task-manager accounts; require a preview before any send, invite, folder, task, reminder, archive, or registry change; and choose where client data is stored and how it can be removed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad enough to match routine project-management requests like status checks, setup, or onboarding, which can cause the skill to activate when the user did not explicitly intend multi-step automation. In this skill’s context, unintended activation is risky because it can cascade into folder creation, calendar events, task creation, and registry updates across multiple connected systems.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly supports creating folders and project structures on local filesystems and cloud storage, but it does not present a strong safety boundary or warning before modifying user data and external services. Because this skill can write to multiple storage backends and create persistent artifacts, accidental or mis-scoped execution could alter, clutter, or overwrite organizational data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill processes client names, emails, budgets, deadlines, and project details, then may propagate that data to email, calendar, task managers, cloud storage, and workspace memory without an upfront warning or consent model. In a client-management context, this increases the risk of unintended disclosure of sensitive business and personal information to third-party services or long-lived memory stores.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal