The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute specific local commands and scripts to ensure analytical rigor.
Evidence:
Use of the date command to establish a verified data cutoff point.
Execution of python3 tools/financial_rigor.py for precise financial arithmetic and scenario modeling.
Use of python3 tools/report_audit.py to perform automated validation of generated research reports.
[PROMPT_INJECTION]: The skill processes external financial data, which constitutes an indirect prompt injection surface.
Ingestion points: The skill ingests user input via $ARGUMENTS and external content from investor reports, regulatory filings, and web searches.
Boundary markers: There are no explicit instructions to wrap or delimit external data to prevent the agent from inadvertently executing instructions hidden within analyzed financial documents.
Capability inventory: The agent possesses the capability to execute workspace-local tools and write persistent report files to the reports/ directory.
Sanitization: The instructions do not specify sanitization or filtering procedures for data retrieved from external web sources or documents.

income-investment