local-docx-editor

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to execute local Python scripts (docx_utils.py, safe_copy.py, sample_docx_edit.py) using a virtual environment to analyze and modify document content.
  • [SAFE]: No evidence of malicious behavior was found. The skill emphasizes data integrity by requiring the creation of working copies in output/working/ and saving final results to output/docx/, ensuring original user files in input/ remain untouched.
  • [PROMPT_INJECTION]: The skill reads external content from user-provided DOCX files, which introduces an indirect prompt injection surface. Ingestion points: DOCX files loaded from the input/ directory. Boundary markers: None; the instructions do not specify delimiters to separate document content from agent instructions. Capability inventory: File system access and local command execution via Python scripts. Sanitization: Not present in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:43 AM
Security Audit — agent-trust-hub — local-docx-editor