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

wps-word

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external data from Word documents using the wps_word_get_document_text tool, establishing a surface for indirect prompt injection. Ingestion points: wps_word_get_document_text referenced in SKILL.md. Boundary markers: Absent; the prompt instructions do not include delimiters or warnings to ignore commands within the document text. Capability inventory: Extensive access to 24 document manipulation tools including file opening and content insertion. Sanitization: Absent; document content is processed directly. This risk is inherent to document processing functionality and is considered low.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 04:02 PM
Security Audit — agent-trust-hub — wps-word