skills/lc2panda/wps-skills/wps-excel/Gen Agent Trust Hub

wps-excel

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it processes data from external spreadsheets that may contain hidden instructions.
  • Ingestion points: Data is ingested via wps_get_active_workbook, wps_get_cell_value, and getRangeData (via wps_execute_method).
  • Boundary markers: No specific boundary markers or instructions are provided to the agent to distinguish between spreadsheet data and system instructions.
  • Capability inventory: The agent can write formulas, delete data, delete worksheets, and unprotect sheets using wps_execute_method.
  • Sanitization: No evidence of data sanitization or validation of spreadsheet content before processing.
  • [COMMAND_EXECUTION]: The skill uses wps_execute_method to perform high-impact operations within the WPS Office environment.
  • Structural Manipulation: Methods such as deleteSheet, deleteRows, and deleteColumns allow for permanent modification of the workbook structure.
  • Security Bypass: The unprotectSheet method allows the agent to remove password protection from worksheets, provided a password is known or supplied.
  • Dynamic Logic: The setFormula method allows the agent to inject and execute Excel-based logic (formulas) across ranges.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 07:27 AM