clean-data-xls
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external spreadsheets, creating a potential surface for indirect prompt injection. 1. Ingestion points: Data enters the agent context from active Excel sheets or specified ranges in SKILL.md. 2. Boundary markers: No specific boundary markers or instructions to ignore embedded content are used. 3. Capability inventory: The skill reads and writes Excel files and executes Python logic using the openpyxl library. 4. Sanitization: No explicit data sanitization or validation of spreadsheet content is described in the workflow.
- [COMMAND_EXECUTION]: The skill involves the execution of Python code with the openpyxl library to process standalone files. 1. Evidence: The environment section specifies using 'Python/openpyxl' for operations on standalone .xlsx files.
Audit Metadata