The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local scripts provided in the skill directory using Node.js (gather.mjs) and Python (render_chart.py) to aggregate data and generate visualizations.- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the mplfinance and pandas Python packages. It also retrieves financial data and institutional activity from external API services including TraderDaddy Pro and TickerTrace.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which constitutes a potential attack surface where malicious content could influence agent behavior.
Ingestion points: Data is ingested from multiple API endpoints providing screener results, options flows, and 13F hedge fund data (SKILL.md).
Boundary markers: No delimiters or instructions are used to separate external data from agent commands or to prevent the agent from following embedded instructions.
Capability inventory: The skill execution environment allows for shell command execution, network requests, and file system interaction.
Sanitization: No content validation or sanitization is mentioned for the data retrieved from the financial APIs before it is analyzed by the agent.

stock-recap