ClawHub
Back to skill

Security audit

Excel 清洗方案台

Security checks for vulnerabilities and agentic risk

Overview

This is a benign Excel data-cleaning guidance skill, with only minor routing ambiguity from broad trigger phrases.

Safe to install for Excel cleaning advice. Users should still avoid pasting unnecessary sensitive spreadsheet contents and should be aware that broad phrases like general duplicate-data or table-organizing requests may activate this skill.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger keywords include broad everyday phrases such as '数据很乱' and '重复数据' that can appear in normal conversation outside the intended skill scope. This can cause unintended activation, leading the agent to route user input into this skill when the user did not explicitly ask for Excel-cleaning guidance, which may confuse workflows or expose unrelated conversation context to the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language examples include ambiguous follow-up phrases like '按上面的结果改成更简短的版本' and '把这些整理成一张表', which are common instructions that could match many unrelated interactions. If used by an agentic router, these examples broaden activation far beyond the skill's intended Excel-cleaning use case and increase the chance of accidental invocation and context misrouting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.