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

wps-ppt

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external PPT files, establishing a surface for indirect prompt injection where untrusted content could influence agent behavior. (1) Ingestion points: Content is retrieved from slides via wps_ppt_get_slide_info, wps_ppt_get_shapes, and wps_ppt_get_slide_notes (SKILL.md). (2) Boundary markers: Absent; no specific delimiters or guardrails are defined to separate slide data from instructions. (3) Capability inventory: The agent has extensive file system and content modification capabilities including wps_ppt_open_presentation and wps_ppt_export_slide_as_image. (4) Sanitization: Absent; text retrieved from files is used in the agent context without escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:04 AM