xlsx-author
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate Python scripts at runtime and execute them via shell commands to produce Excel files. This is a functional requirement for the skill's purpose and follows simple templates.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection through data ingestion into spreadsheets. Ingestion points: User-provided data is interpolated into generated Python scripts for cell values and formulas. Capability inventory: The agent utilizes bash execution and file system writes. Boundary markers: No specific delimiters are used to separate user data from instructions. Sanitization: No validation or escaping is applied to data before inclusion in spreadsheet formulas.
Audit Metadata