clean-data-xls
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the 'openpyxl' library from the Python Package Index (PyPI). This is a well-known, standard package for handling Excel files and is necessary for the skill's primary function.
- [COMMAND_EXECUTION]: Shell commands are used to check for and install required Python dependencies. These operations are limited to environment setup and do not interpolate untrusted input.
- [PROMPT_INJECTION]: The skill processes untrusted spreadsheet data, which presents a surface for indirect prompt injection (Category 8). An attacker could place malicious instructions in cells that an agent might inadvertently follow during processing.
- Ingestion points: Data from active sheets or standalone xlsx files.
- Boundary markers: None explicitly defined to separate data from instructions.
- Capability inventory: Python script execution, Office JS interaction, and shell command execution.
- Sanitization: No explicit sanitization of cell content is described.
- Mitigation: The workflow requires user confirmation before applying changes and showing samples, providing a critical safety checkpoint.
Audit Metadata