pivot-table-generator

Warn

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (MEDIUM): The skill processes untrusted external CSV data which can be used to inject instructions into the agent's context during data analysis.
  • Ingestion points: The scripts/pivot_table_generator.py file reads external data using pd.read_csv(args.data) at line 86.
  • Boundary markers: Absent. The data is parsed directly into a pandas DataFrame without delimiters or instructions to the agent to ignore embedded content.
  • Capability inventory: The script has the capability to read local files via pd.read_csv and write to the local filesystem using to_csv, to_excel, to_html, and plt.savefig (lines 53-61, 70-76).
  • Sanitization: Absent. The script relies on standard pandas parsing which does not filter for Natural Language instructions embedded in data fields.
  • [Data Exposure] (LOW): The script accepts arbitrary file paths via CLI arguments for both input (--data) and output (--output). An attacker could potentially trick the agent into reading sensitive configuration files as CSVs or overwriting critical files with pivot table data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 11:44 PM