xlsx-manipulation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which could potentially contain malicious instructions designed to influence the AI agent's behavior.
- Ingestion points: The skill documentation (SKILL.md) illustrates reading data through
load_workbook()for Excel files andcsv.reader()for CSV imports. - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to treat spreadsheet content as pure data and ignore any embedded instructions.
- Capability inventory: The skill involves file-write operations (
wb.save()) and the execution of generated Python scripts. - Sanitization: No data validation or sanitization mechanisms are described for handling cell content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill's primary operational mode involves the agent generating and executing Python code at runtime to interact with the openpyxl library.
Audit Metadata