ClawHub
Back to skill

Security audit

pagesskill

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for building NocoBase pages, but its broad auto-triggers and direct destructive page/menu tools need careful review before installation.

Install this only for agents that should be allowed to change NocoBase UI structure. Require explicit user confirmation before deleting routes, cleaning/rebuilding layouts, removing fields or columns, or adding JS/event-flow behavior, and prefer narrowing the triggers to NocoBase-specific page-building requests.

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
  • 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 (7)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list contains very broad terms such as "页面", "page", and especially "form", which can cause this skill to activate in many unrelated conversations. Because the skill exposes powerful page-building and modification tools, unintended invocation can lead to unauthorized UI changes, destructive actions, or accidental execution of high-impact operations in contexts where the user did not explicitly request them.

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding

Shadow Command Trigger: 'build page' conflicts with built-in command 'build'

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding

Shadow Command Trigger: 'create menu' conflicts with built-in command 'create'

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documents direct use of nb_delete_route to remove menu items, including deleting a group and its children, but provides no requirement for explicit confirmation, preview of affected routes, or rollback guidance. In an agent-driven workflow, this increases the chance of accidental or misunderstood destructive operations that can remove navigation structure or associated page access unexpectedly.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: '页面' is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: '区块' is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: '大纲' is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.