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

wps-ppt

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection during the processing of existing presentation data.\n
  • Ingestion points: Untrusted content is ingested into the agent context from PowerPoint files via tools such as wps_ppt_get_slide_info, wps_ppt_get_slide_notes, and wps_ppt_find_ppt_text.\n
  • Boundary markers: The instructions lack specific delimiters or directives to isolate content retrieved from slides from the agent's core instructions, increasing the risk of the agent obeying instructions embedded in the PPT.\n
  • Capability inventory: The skill has extensive file manipulation capabilities within the WPS environment, including the ability to delete slides (wps_ppt_delete_slide) and modify all slide content.\n
  • Sanitization: No sanitization or validation of the retrieved text is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 01:20 PM
Security Audit — agent-trust-hub — wps-ppt