The Agent Skills Directory

[SAFE]: The skill instructions and associated reference files are strictly focused on financial modeling and valuation logic. There is no evidence of credential harvesting, unauthorized network operations, or malicious command execution.
[PROMPT_INJECTION]: The skill handles data from external tools (get_financials and get_market_data), creating a surface for potential indirect prompt injection. However, the risk is negligible as the skill only performs mathematical calculations and data presentation.
Ingestion points: Financial metrics and statements retrieved from project-defined tools in SKILL.md.
Boundary markers: Absent; data is processed as part of the natural language workflow.
Capability inventory: The skill's capabilities are limited to mathematical computation, formatting tables, and presenting analysis to the user.
Sanitization: Not explicitly present, though the limited scope of action mitigates risk.

dcf-valuation