The Agent Skills Directory

[COMMAND_EXECUTION]: Uses dynamic context injection (the !command syntax) in SKILL.md to execute a shell command that checks for the presence of the yfinance package when the skill is loaded.
[COMMAND_EXECUTION]: Instructs the agent to utilize the subprocess module to run pip install for the yfinance library if it is not already installed in the environment.
[EXTERNAL_DOWNLOADS]: Fetches and installs the yfinance package from the official Python Package Index (PyPI) to support financial data retrieval.
[PROMPT_INJECTION]: Subject to indirect prompt injection risks as the skill ingests and summarizes external news data via the ticker.news API.
Ingestion points: External news headlines are retrieved from ticker.news in SKILL.md and references/api_reference.md.
Boundary markers: None present; the skill does not use delimiters or specific instructions to ignore malicious content embedded within the fetched headlines.
Capability inventory: The skill environment allows for Python code execution and shell command execution via subprocess.
Sanitization: No validation, filtering, or escaping is performed on the news data before it is presented in the final summary.

earnings-recap