The Agent Skills Directory

[SAFE]: The skill is a purely instructional markdown file that guides an AI agent through a backtesting audit process. It does not include any scripts, external dependencies, or command execution steps.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting user-supplied trading strategy definitions. While this constitutes an input surface, the skill lacks any associated side effects or high-privilege capabilities (such as file system writes or network requests) that would make this surface exploitable. The focus is strictly on generating an analytical report.
[SAFE]: The logic documented (survivorship bias auditing, look-ahead bias checks, and transaction cost modeling) follows standard industry best practices for quantitative analysis and does not introduce security risks.

quant-backtest