Skills
skills/starchild-ai-agent/official-skills/backtest/Gen Agent Trust Hub

backtest

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the bash tool to execute Python scripts that are dynamically generated to perform financial backtesting.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill incorporates untrusted data into the execution flow.
  • Ingestion points: User-defined entry/exit rules and existing scripts in the scripts/ directory (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: The skill uses the bash, write_file, and read_file tools (SKILL.md).
  • Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: Installs the standard and well-known Python libraries mplfinance, pandas, and numpy from official sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 05:09 AM