data-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The utility script scripts/query.sh facilitates the execution of SQL commands through system-level database clients including sqlite3, psql, and mysql. This capability allows the agent to query and manipulate data in configured databases as part of its primary function.
  • [COMMAND_EXECUTION]: The initialization script scripts/data-init.sh performs workspace setup by creating directories and generating template files using mkdir, cat, and chmod. These operations are localized to the user's home directory.
  • [SAFE]: The skill manages an attack surface for indirect prompt injection through the ingestion of external data files and database outputs. Ingestion points: CSV and Excel file processing in scripts/analyze_template.py and database result processing in scripts/query.sh. Boundary markers: Absent; the skill does not explicitly differentiate between data content and potential embedded instructions. Capability inventory: The skill can execute database queries and perform filesystem writes within its designated workspace. Sanitization: No specific sanitization or validation logic for external data inputs was identified in the provided templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:14 PM