working-with-spreadsheets

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious code, hardcoded credentials, or unauthorized external references were detected. The skill's behavior is consistent with its stated purpose of spreadsheet modeling and data analysis.
  • PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface. The skill involves ingesting untrusted data from external Excel files, creating a potential surface for indirect prompt injection attacks if the spreadsheet content contains adversarial instructions.
  • Ingestion points: Use of pd.read_excel and load_workbook in SKILL.md to process external .xlsx files.
  • Boundary markers: Absent; the skill does not include specific delimiters or instructions to ignore embedded commands within the data.
  • Capability inventory: File system write access (wb.save) is demonstrated in multiple examples.
  • Sanitization: Absent; no logic is provided to sanitize or validate the content of the spreadsheet cells before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:09 PM