excel-lbo-modeler

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are focused entirely on professional financial modeling tasks. No evidence of prompt injection, data exfiltration, or malicious persistence was found.
  • [COMMAND_EXECUTION]: The skill utilizes an external MCP server (@negokaz/excel-mcp-server) to perform Excel operations. This tool usage is transparently documented in the prerequisites and is required for the skill's primary function of building spreadsheets.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data collected through natural language queries.
  • Ingestion points: User-provided inputs such as target company name and financial metrics are gathered via AskUserQuestion in Step 1.
  • Boundary markers: None explicitly defined for user inputs.
  • Capability inventory: File system operations (Write, Edit) and tool execution via the Excel MCP server.
  • Sanitization: The skill includes a dedicated validation step (Step 2) that filters inputs based on realistic industry ranges (e.g., verifying multiples between 6-15x and leverage below 7x), which mitigates risks from malformed or malicious data inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 10:27 AM
Security Audit — agent-trust-hub — excel-lbo-modeler