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.py to 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 openpyxl library, 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
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:28 PM
Security Audit — agent-trust-hub — lbo-model