earnings-preview
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses dynamic context injection to run a shell command during initialization. This command checks the version of the yfinance library in the current environment.\n- [COMMAND_EXECUTION]: The skill executes Python subprocess calls to run pip commands for installing dependencies. This is a common pattern for managing required libraries at runtime.\n- [EXTERNAL_DOWNLOADS]: The skill fetches the yfinance package from the Python Package Index (PyPI). This is a well-known library used for its intended purpose of retrieving financial data.\n- [PROMPT_INJECTION]: The skill retrieves financial metrics from an external source (Yahoo Finance) and incorporates them into the agent's context, creating a surface for indirect prompt injection.\n
- Ingestion points: Financial data, estimates, and analyst sentiment are fetched from the yfinance API in SKILL.md.\n
- Boundary markers: There are no explicit delimiters used to isolate the fetched external data from the skill's instructions.\n
- Capability inventory: The skill has access to shell execution and Python execution environments.\n
- Sanitization: No sanitization or validation of the external data is performed before it is presented to the user.
Audit Metadata