ClawHub
Back to skill

Security audit

Plashboard Admin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Plashboard administration helper that can make live dashboard changes, but its behavior is coherent with its stated purpose and scoped to Plashboard tools.

Install this only if you want an agent to administer Plashboard directly. Be aware that ordinary dashboard requests may create, activate, and run a live dashboard immediately, and deletion or activation commands can persistently change Plashboard state.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The intent automation explicitly instructs the agent to onboard, activate, and run a dashboard immediately from a natural-language request, with no warning or confirmation despite clear side effects. This is more dangerous in context because the skill is built for autonomous tool dispatch and prefers execution over clarification, making accidental or over-broad production changes much more likely.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata and description position the skill to autonomously manage dashboards, including creating and activating live configurations, without any explicit requirement to warn the user or obtain confirmation before making live changes. In an agentic/tool-dispatch context, this can cause unintended production modifications from natural-language requests, especially when users may not realize actions are immediately operationalized.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Documenting activate and delete capabilities without any cautionary guidance normalizes destructive and live-impacting actions as routine operations. In a skill designed to prefer direct tool execution, the absence of safety messaging or confirmation steps increases the risk of accidental template deletion or unintended activation of a new live dashboard.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.