excel-fixer

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill ingests data from external CSV and Excel files in SKILL.md via pd.read_csv and load_workbook.
  • Boundary markers: No delimiters or instructions are present to prevent the agent from potentially interpreting data within cells as commands.
  • Capability inventory: The skill has local file system write capabilities using pandas.to_csv and openpyxl.save.
  • Sanitization: The skill does not sanitize or escape cell content before processing or generating the summary report.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM