The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of an external Python script, recalc.py, to perform formula validation and recalculation on generated Excel files. The agent is instructed to run this script using a shell command (python recalc.py [path] [timeout]) before final delivery.
[INDIRECT_PROMPT_INJECTION]: The skill has a defined attack surface for indirect prompt injection as it ingests data from external, untrusted sources including web searches and analyst reports.
Ingestion points: Data is retrieved from SEC filings, analyst reports, and general web searches via search tools and MCP servers (e.g., Daloopa).
Boundary markers: The instructions do not specify the use of delimiters or boundary markers to separate external data from agent instructions.
Capability inventory: The skill has the ability to write to the file system (creating .xlsx models) and execute shell commands (running recalc.py).
Sanitization: There are no explicit instructions for sanitizing or filtering instructions that might be embedded in retrieved financial documents or web content.
[EXTERNAL_DOWNLOADS]: The skill relies on external data sourcing from MCP servers and web fetching to gather current market prices, beta values, and historical financial metrics from third-party providers.

dcf-model