lbo-model
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local utility script at
/mnt/skills/public/xlsx/recalc.pyto perform formula recalculation and validation on generated Excel files. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external Excel templates and financial assumption data provided by the user.
- Ingestion points: Ingests user-provided financial data and Excel template files (e.g.,
LBO_Model.xlsx). - Boundary markers: The instructions do not include specific delimiters or directives for the agent to ignore instructions potentially embedded within the ingested data.
- Capability inventory: The skill can write to the local file system using the
openpyxllibrary, execute Python scripts, and interact with the Excel environment via Office JS. - Sanitization: There are no explicit instructions for sanitizing or validating input data before it is formatted into Excel formulas.
Audit Metadata