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

wps-office

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing data from external WPS files (Word, Excel, and PowerPoint).
  • Ingestion points: The agent reads untrusted data using tools such as wps_word_get_document_text, wps_excel_read_range, and wps_ppt_get_slide_info as described in SKILL.md.
  • Boundary markers: Absent. There are no instructions or delimiters defined to help the agent distinguish between the developer's instructions and potentially malicious instructions embedded within the documents it processes.
  • Capability inventory: High. The skill has the ability to write to files (wps_word_insert_text, wps_excel_write_range), perform format conversions (wps_convert_format), and manage applications, which could be abused if an injected instruction is followed.
  • Sanitization: Absent. Content read from files is not validated or sanitized before being processed or used to influence subsequent agent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:15 AM