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

wps-ppt

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface (Category 8) because it reads and processes user-controlled content from existing presentations.
  • Ingestion points: The skill reads slide content, text boxes, and speaker notes via tools like wps_get_active_presentation, getTextBoxes, and getSlideNotes.
  • Boundary markers: No explicit delimiters or instructions for the agent to ignore instructions embedded within the PPT data are present.
  • Capability inventory: The agent can modify files, insert text, and create hyperlinks through the wps_execute_method and addPptHyperlink tools.
  • Sanitization: No validation or filtering of ingested text content is described.
  • [COMMAND_EXECUTION]: The skill uses a generic wps_execute_method tool to perform operations. These operations are restricted to the WPS Office application context (specified via appType: "wpp") and do not allow for arbitrary system shell command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 07:27 AM