The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage its environment and run analysis scripts. Evidence found in references/data-queries.md includes commands for activating a virtual environment and executing Python scripts such as stock_data.py and sec_edgar.py located in a sibling directory (../findata-toolkit/).
[EXTERNAL_DOWNLOADS]: The skill configuration requires the agent to install Python dependencies from a local requirements file using pip, which involves fetching software packages from external registries like PyPI. This is documented in the setup instructions in references/data-queries.md.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external, potentially attacker-influenced sources such as SEC EDGAR filings.
Ingestion points: External financial data and SEC filings are fetched using the scripts listed in references/data-queries.md.
Boundary markers: The provided documentation does not specify the use of delimiters or instructions to ignore embedded commands within the processed data.
Capability inventory: The skill has the capability to execute shell commands and perform file-based data processing through its associated toolkit.
Sanitization: No sanitization or validation logic is present in the provided files to filter malicious content from the ingested financial data.

dividend-aristocrat-calculator