skills/lc2panda/wps-mcp/wps-office/Gen Agent Trust Hub

wps-office

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides tools for local office automation, including application state management (wps_office_check_status), file operations (wps_office_open_file, wps_office_save_as), and printing. These capabilities are within the expected scope for a WPS Office integration and use the consistent vendor namespace 'wps_office_*'.
  • [PROMPT_INJECTION]: As an assistant that processes external files, the skill has a surface for indirect prompt injection (Category 8) where malicious instructions in a document could influence agent behavior.
  • Ingestion points: The skill reads content from Word documents, Excel spreadsheets, and directory listings (e.g., 'Scenario 2: Word内容生成PPT', 'Scenario 3: 批量格式转换').
  • Boundary markers: None specified; the skill instructions do not define delimiters or specific 'ignore' instructions for content parsed from files.
  • Capability inventory: Includes file system access (read/write), printing, exporting documents, and control over multiple office applications.
  • Sanitization: There is no mention of sanitization, filtering, or validation of the text content extracted from processed documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 07:47 AM