spreadsheet-formula-helper

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation describes using the openpyxl Python library for local spreadsheet inspection. This is a standard and appropriate tool given the skill's primary function of formula generation and debugging.
  • [EXTERNAL_DOWNLOADS]: The changelog contains a reference to the skill's original source repository (github.com/ComposioHQ/awesome-codex-skills). This is a legitimate documentation of the skill's origin and does not involve risky remote code downloads or execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting spreadsheet data and inspecting workbooks, which creates a surface for potential indirect prompt injection.
  • Ingestion points: Sample data ranges and Excel workbooks analyzed during the workflow and fallback processes.
  • Boundary markers: The instructions do not specify explicit delimiters to separate external data from agent instructions.
  • Capability inventory: The skill uses local libraries for data inspection but does not have access to high-risk tools like network requests or shell command execution.
  • Sanitization: No specific content sanitization or validation protocols are mentioned for the spreadsheet data processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 01:39 AM
Security Audit — agent-trust-hub — spreadsheet-formula-helper