skills/coppermare/skillverse/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is sourced from the official Anthropic skills repository, which is a verified and trusted source for agent capabilities.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes well-known and reputable Python packages, specifically pandas and openpyxl, for spreadsheet data manipulation and formatting tasks.\n- [COMMAND_EXECUTION]: The skill includes instructions to execute a local Python script, recalc.py, to handle formula recalculation via LibreOffice as part of its documented spreadsheet processing workflow.\n- [PROMPT_INJECTION]: The skill processes external spreadsheet data (Excel, CSV, TSV), which constitutes an ingestion point for untrusted content. Mandatory Evidence Chain:\n
  • Ingestion points: File reading operations via pandas and openpyxl as described in SKILL.md.\n
  • Boundary markers: No specific delimiters or boundary instructions are defined for the data contents in the provided instructions.\n
  • Capability inventory: The skill possesses the capability to perform file system write operations and execute the recalc.py script.\n
  • Sanitization: No sanitization or validation logic for the processed spreadsheet data is explicitly described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:37 AM
Security Audit — agent-trust-hub — xlsx