spreadsheet-modeling

Warn

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md direct the AI agent to perform environment discovery by executing shell commands. The "Companion check" section specifically instructs the agent to run ls on multiple filesystem paths, including ~/.claude/skills/, ~/.agent/skills/, and ~/.agents/skills/. This allows the agent to probe the user's environment for other installed skills without an explicit user command for filesystem access.
  • [EXTERNAL_DOWNLOADS]: The reference documentation includes code patterns for establishing network connectivity from within automated scripts. references/vba-patterns.md provides implementation details for making HTTP GET requests using MSXML2.XMLHTTP in Excel VBA and using UrlFetchApp.fetch() in Google Apps Script to interact with external APIs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 10, 2026, 02:05 PM
Security Audit — agent-trust-hub — spreadsheet-modeling