ClawHub
Back to skill

Security audit

Excel工具(免费版)

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Excel helper that works locally, but it can run Python and create modified spreadsheet files.

Install only if you want an agent to process Excel files with local Python. Provide explicit spreadsheet paths, prefer new output filenames, review generated scripts before execution when the spreadsheet is sensitive, and avoid using it for generic analysis tasks that do not involve Excel/xlsx files.

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 (4)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description is broad enough that an agent may invoke it for loosely related tasks without clear user intent, increasing the chance of inappropriate file access or modification. In a skill that can read, write, and execute code against user-provided files, ambiguous activation criteria raise the risk of unintended operations on sensitive local data.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The keyword coverage section uses an expansive, fragmented keyword list that can cause over-triggering for unrelated prompts. Because the skill supports file reads/writes and code execution, overly broad matching increases the likelihood that the agent performs spreadsheet operations or generates code in contexts the user did not clearly authorize.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill describes write/export behavior without a clear warning that it may create or overwrite Excel files. Users may unknowingly permit destructive file changes, leading to data loss or accidental modification of important spreadsheets, especially when combined with broad invocation scope.

Missing User Warnings

High
Confidence
97% confidence
Finding
The documentation states the agent will generate and execute Python scripts against user files but does not prominently warn users about this execution model. This is dangerous because executing generated code materially expands the attack surface: prompt misinterpretation, unsafe path handling, or future code-generation errors could lead to unintended file access, modification, or local command execution.

Static analysis

No suspicious patterns detected.