ClawHub
Back to skill

Security audit

Excel

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Excel-helper skill whose disclosed behavior matches its purpose, with no evidence of hidden execution, persistence, credential access, or exfiltration.

Install this if you want a Chinese-language Excel assistant. Because it can write spreadsheets, give explicit instructions about whether changes should be saved in place or to a new file, especially for business or financial workbooks.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: "00000000000000000000000000000000"
    PropagateID: "00000000000000000000000000000000"
    ReservedCode1: 3046022100ac34ac1e12efb617f5ab736ad62a1f16cb2ade4f6b19796ee8a9d7fc421d0afb022100efd843b604cc44829352eb6f37745741ed47da3b1fa1614417891b2ba00ddd56
    ReservedCode2: 30440220365cf65881d3b47bf094dd95ebfe66fb9a6b45108762bdc7f6bce708c5e83df902207dc67abc23cd7263379f2bc59e6e973b3a1975e24908ee25fda44fa30ec266f5
description: Excel 操作。数据处理、公式、表格操作。
metadata:
    category: 数据分析
    emoji: "\U0001F4D7"
    triggers:
        - Excel
        - excel
        - 表格
        - csv
        - xlsx
name: excel
---

# Excel 技能

帮你处理 Excel 文件。

## 功能
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list is broad enough to match common terms like 'excel', 'csv', and '表格', which can cause the skill to activate in contexts where the user did not explicitly request this capability. Unintended invocation can expose local data paths or lead to accidental file processing/modification if the surrounding agent automatically routes tasks based on trigger terms.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises read/write Excel capability but provides no warning that operations may alter user data. In an agent environment, this increases the chance of silent or unexpected file modification, overwrites, or propagation of incorrect transformations to business data.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The user-facing description and usage instructions are entirely in Chinese, and there is no indication that other languages are supported or that the user may choose their preferred language. This can be a language-policy issue when the skill implicitly constrains interaction to a single language without opt-in.

Static analysis

No suspicious patterns detected.