skills/openclaw/skills/office-mcp/Gen Agent Trust Hub

office-mcp

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References the official Anthropics skills repository for resources and documentation. Dependencies such as python-docx, openpyxl, and reportlab are well-known libraries for document processing sourced from official package registries.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data into document templates without explicit security boundaries.
  • Ingestion points: User-provided content strings ingested by the create_docx and edit_docx tools defined in SKILL.md.
  • Boundary markers: The implementation snippets do not include delimiters or instructions to ignore instructions embedded within the document content.
  • Capability inventory: The skill performs file system write operations using the .save() methods of the Word and Excel libraries.
  • Sanitization: No validation or escaping of the user-supplied content is performed before it is added to the document structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 02:33 AM