docx-processor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it ingests untrusted data from external Word documents.
  • Ingestion points: scripts/read_docx.py and scripts/convert_docx.py read text, tables, and styles from user-provided .docx files.
  • Boundary markers: Absent. The extracted content is passed to the agent without delimiters or warnings to ignore instructions embedded within the document.
  • Capability inventory: The skill possesses file-read capabilities (any path provided by the user) and file-write capabilities (writing converted results to /tmp/openskills-converted/).
  • Sanitization: Absent. The Python scripts extract raw text from XML structures and return it directly to the agent's context.
  • COMMAND_EXECUTION (SAFE): While the scripts perform file system operations (read/write), they are restricted to the intended purpose of document processing. The use of pathlib.Path.expanduser() is standard for handling user-provided file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM