word-document
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Word documents (.docx), which constitutes an attack surface for indirect prompt injection where malicious instructions could be embedded in document data.\n
- Ingestion points: The skill is activated for reading and editing reports, memos, and structured deliverables in .docx format.\n
- Boundary markers: There are no specific instructions or delimiters provided to ensure the agent ignores or sanitizes instructions that might be present within the processed document content.\n
- Capability inventory: The skill has the capability to write files to the local system (e.g., using 'fs.writeFileSync' in Node.js examples and 'mcp_word_save_document' in script fallbacks).\n
- Sanitization: No explicit sanitization, validation, or filtering mechanisms are described for document content before it is processed or used to generate new output.
Audit Metadata