hedgefund-bain-competitive
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local environment by instructing the agent to execute a Python script located at an absolute path:
/Users/engineer/.venv/bin/python3 .agents/skills/stocks-advisor/scripts/fundamentals.py. This script is utilized to fetch live financial fundamentals for identified stock tickers.\n- [PROMPT_INJECTION]: The skill involves fetching and processing data from third-party web sources, which introduces a potential surface for indirect prompt injection.\n - Ingestion points: Untrusted data enters the context via
web_fetchfrom sources such as IDC, Gartner, Statista, and company annual reports.\n - Boundary markers: Absent; the instructions do not specify the use of delimiters or ignore-instructions for the external content.\n
- Capability inventory: The skill has access to shell execution via a Python interpreter and general network access via
web_fetch.\n - Sanitization: No explicit sanitization or validation of the external web content is described prior to its inclusion in the analysis.
Audit Metadata