hedgefund-morgan-stanley-dcf
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute shell commands to create cache directories, write configuration files, and run a Python script for data retrieval.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the
yfinancelibrary to download historical financial statements and market data from Yahoo Finance at runtime.\n- [PROMPT_INJECTION]: The skill ingests data from external financial APIs, creating a potential surface for indirect prompt injection via malformed market data.\n - Ingestion points: External data is ingested through the
yfinancelibrary withinscripts/dcf_pull.py.\n - Boundary markers: Instructions specify that all data points must be grounded in history and explicitly labeled, with a requirement to stop execution if core data is missing.\n
- Capability inventory: The skill scripts and instructions perform file writes, directory management, and network communication for data retrieval.\n
- Sanitization: The Python script performs validation on the ticker symbol (checking for whitespace and commas) and converts inconsistent API returns into standard null values to maintain data integrity.
Audit Metadata