skills/owid/etl/streamlit-app/Gen Agent Trust Hub

streamlit-app

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates code generation and modification, which naturally presents an indirect prompt injection surface. This is expected for a development-focused skill.\n
  • Ingestion points: User instructions for Streamlit app logic and configuration.\n
  • Boundary markers: None explicitly defined for user input interpolation.\n
  • Capability inventory: File writing in apps/wizard/app_pages/, database access via etl.db, and utility execution.\n
  • Sanitization: No specific instructions are provided for sanitizing user input before it is written to scripts, though standard Streamlit and Python best practices are assumed.\n- [COMMAND_EXECUTION]: The documentation describes executing the developed applications using local shell commands like make wizard or scripts within a virtual environment, which is necessary for the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 05:35 PM