The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external financial datasets and market time series, which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: The skill ingests historical price/returns data, market microstructure data, and order book dynamics (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers for external data processing are mentioned in the instructions.
Capability inventory: The skill utilizes scientific libraries including pandas, numpy, scipy.optimize, and cvxpy for statistical modeling and strategy execution (SKILL.md).
Sanitization: No explicit sanitization or validation routines for external financial data are described.
[SAFE]: The skill's instructions are focused entirely on legitimate financial engineering and quantitative development workflows. All mentioned tools and libraries are standard in the data science domain, and no suspicious network or file system operations were found.

quant-analyst