The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data fetched from an external API, which introduces a surface for indirect prompt injection.\n
Ingestion points: Data is retrieved from the Financial Modeling Prep API via the fetch_earnings_fmp.py script and can also be provided through manual entry in fallback mode.\n
Boundary markers: The skill uses structured markdown tables for data presentation but lacks explicit boundary markers or instructions to the agent to disregard potential instructions within the data fields.\n
Capability inventory: The skill has the capability to execute local Python scripts (fetch_earnings_fmp.py, generate_report.py) and perform network operations via the requests library.\n
Sanitization: While the scripts perform data normalization and formatting, there is no explicit sanitization logic to detect or neutralize malicious instructions embedded in the API response fields like company names or sector descriptions.\n- [EXTERNAL_DOWNLOADS]: The skill connects to an external API to retrieve financial data.\n
Evidence: The script scripts/fetch_earnings_fmp.py makes HTTP GET requests to the financialmodelingprep.com domain to fetch earnings calendars and company profiles.\n- [COMMAND_EXECUTION]: The skill utilizes local Python scripts to perform data retrieval and report generation.\n
Evidence: SKILL.md instructs the agent to run python scripts/fetch_earnings_fmp.py and python scripts/generate_report.py as part of the core workflow.

earnings-calendar