docx
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and manipulate external Word documents (.docx), which represents a potential attack surface for indirect prompt injection if documents contain hidden instructions.
- Ingestion points: Processes contents of .docx files as specified in the skill description and instructions in SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between document data and potentially malicious embedded commands.
- Capability inventory: The skill is intended to perform file read/write operations using the
python-docxlibrary. - Sanitization: No specific sanitization, filtering, or validation of document content is described in the guidelines.
Audit Metadata