ClawHub

excel-table-structurer

Security checks across malware telemetry and agentic risk

Overview

This skill locally restructures uploaded Excel workbooks and creates a formatted output file, with no evidence of hidden network access, credential access, persistence, or destructive behavior.

Install only if you want automated restructuring of hierarchical Excel files. Before use, confirm the workbook, sheet, columns, and output filename, and review the generated workbook because fill-down and group transformations can change how spreadsheet meaning is displayed.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description uses broad trigger phrases such as '整理表格' and '清理表格格式', which can match many ordinary spreadsheet requests and cause the skill to activate in contexts the user did not intend. Because the skill reads and rewrites uploaded .xlsx files, overbroad invocation increases the chance of unintended file modification, incorrect transformation, or privacy exposure from processing sensitive spreadsheets.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow instructs the agent to read the uploaded Excel file, construct a transformation spec, run a restructuring script, and send back a modified output, but it does not require an explicit user warning that the original content will be transformed and a new file generated. This is risky because spreadsheet restructuring can alter meaning, duplicate values via fill-down, or expose hidden relationships, and users may not understand that the operation is destructive or inferential rather than a passive review.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal