ClawHub
Back to skill

Security audit

Pro Comm Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

This is mostly a workplace writing template skill, but it asks for command execution and uses action-oriented triggers like sending messages and notifications without clear limits.

Review before installing. The artifact does not show malicious code, persistence, credential handling, or exfiltration, but it requests shell execution for a writing-only use case and describes triggers that sound like sending or integrating communications. Install only if you are comfortable constraining it to drafting tasks and denying unexpected command execution or message-delivery actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill requests `exec` capability even though its stated purpose is generating writing templates and communication guidance, which does not inherently require shell execution. Granting command execution to a content-only assistant unnecessarily expands the attack surface and could enable harmful command invocation if the skill is triggered or extended in unsafe ways.

Description-Behavior Mismatch

Medium
Confidence
88% confidence
Finding
The documentation broadens the skill from a writing assistant into message sending, notification pushing, email/SMS, and communication integration scenarios. This scope expansion increases the chance that an agent may treat the skill as authorized to perform external communications or automation beyond safe text drafting, which can lead to unintended actions or abuse if paired with tool access.

Intent-Code Divergence

Medium
Confidence
91% confidence
Finding
The skill describes itself as 'pure Markdown instruction driven' while also classifying itself as `MD+EXEC` and claiming some functions require command execution. This inconsistency obscures the true trust boundary and may cause reviewers or users to underestimate operational risk, especially when combined with unnecessary `exec` permissions.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger condition is broad enough to match generic communication, notification, email, SMS, and integration requests, making accidental or overbroad invocation more likely. In a skill with ambiguous scope and declared execution capability, overly permissive triggering increases the risk that the agent routes unrelated tasks into a more privileged or action-implying workflow than intended.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.