indicator-dashboard

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates within the expected bounds of a technical analysis dashboard builder. All external references are to well-known libraries and local templates.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to run the generated dashboard applications (e.g., 'python app.py' or 'streamlit run app.py'). This is an intended and documented functionality of the skill.\n- [DATA_EXFILTRATION]: The generated code is instructed to load '.env' files using 'find_dotenv()'. While this involves accessing potentially sensitive configuration files, it is the standard and necessary method for retrieving API credentials for financial data providers.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by interpolating user-provided symbols and types into the generated Python code.\n
  • Ingestion points: User input via $ARGUMENTS ($0 for dashboard type, $1 for symbol).\n
  • Boundary markers: None specified in the instructions for the generated script.\n
  • Capability inventory: The skill possesses 'Write' permissions to create executable Python files and 'Bash' permissions to run them.\n
  • Sanitization: No explicit sanitization or validation of the symbol or type input is described in the instruction set, relying on the agent's code generation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:23 AM