ClawHub
Back to skill

Security audit

MetricHub 指标平台

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent MetricHub helper skill with disclosed platform workflows, though dashboard and Gateway changes should be confirmed before use.

Install this skill only if you want an agent to help operate MetricHub. Before allowing write actions, confirm the workspace, role, target dashboard, and Gateway/API-key setting; keep API keys inside the trusted MetricHub settings flow.

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
  • 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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description includes broad trigger phrases such as querying metrics, comparisons, rankings, browsing catalog, creating dashboards, and configuring Gateway without clear activation boundaries. This can cause the skill to activate on ordinary analytical conversations and potentially steer the agent into sensitive read/write actions in a multi-tenant workspace, especially around dashboard creation and Gateway configuration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents create and modify dashboard operations in a workspace but does not require an explicit user warning or confirmation before performing write actions. In a multi-tenant environment, silent execution of these operations can lead to unauthorized or accidental modification of shared workspace assets.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The routing table maps short, ambiguous natural-language phrases directly to application routes, including state-changing or sensitive areas like dashboards and Gateway settings. Without clearer boundaries, normal user requests could trigger navigation or workflow suggestions that expose administrative surfaces or encourage unintended operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.