The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from external sources such as company websites and financial filings.
Ingestion points: Company research workflow involves fetching data from various external public domains (e.g., company IR pages, news articles).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the external content processed by the agent.
Capability inventory: The skill utilizes file system operations (DOCX), spreadsheet processing (XLSX), and Python code execution for visualizations.
Sanitization: No explicit sanitization or validation of the external content is described in the workflow.
[REMOTE_CODE_EXECUTION]: The skill employs template-based Python script generation to create financial charts and visualizations.
Evidence: The file references/task4-chart-generation.md contains detailed Python code blocks for generating various charts (Revenue, DCF, Football Field) using common libraries like matplotlib and seaborn. These templates are part of the skill's core functionality for data presentation.

initiating-coverage