skills/hmbown/codewhale/spreadsheets/Gen Agent Trust Hub

spreadsheets

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard data processing tools and libraries (Python, LibreOffice) to manipulate spreadsheet files. These operations are aligned with the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data formats such as XLSX, CSV, and TSV, which constitutes an ingestion surface for untrusted data.
  • Ingestion points: Input spreadsheet files provided by the user.
  • Boundary markers: None explicitly defined within the instructions.
  • Capability inventory: The skill can read and write files and perform data analysis using Python libraries.
  • Sanitization: Not explicitly addressed; the skill focuses on data integrity (e.g., avoiding silent row drops) rather than adversarial content filtering.
  • [EXTERNAL_DOWNLOADS]: The instructions include a specific safety constraint requiring the agent to ask for user permission before installing any missing Python packages or dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:55 PM
Security Audit — agent-trust-hub — spreadsheets