text-to-excel
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied text to generate spreadsheet content, which constitutes an indirect prompt injection attack surface.
- Ingestion points: The skill parses Markdown tables, CSV, JSON, and lists provided by the user in Step 1 of the
SKILL.mdworkflow. - Boundary markers: There are no explicit instructions or delimiters defined to prompt the agent to ignore potentially malicious instructions embedded within the text data.
- Capability inventory: The skill uses
scripts/generate_excel.pyto write Excel files to the local filesystem at a user-defined path. - Sanitization: The Python script performing the generation (
scripts/generate_excel.py) performs type casting for cell values but does not implement security-specific sanitization or filtering of the string content. - [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/generate_excel.py) using a shell command to perform the file generation. This execution is limited to the tool's primary purpose and uses data provided by the user during the session.
Audit Metadata