earnings-team
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts located in the
~/ai-berkshire/tools/directory (e.g.,financial_rigor.pyandreport_audit.py) to perform arithmetic validation, market cap verification, and report auditing. These are used as internal utilities for ensuring data integrity. - [EXTERNAL_DOWNLOADS]: The agent is instructed to fetch financial data, earnings call transcripts, and shareholder letters from reputable external sources including SEC EDGAR (US), HKEX (Hong Kong), CNINFO (China), Seeking Alpha, and official company IR pages.
- [DATA_EXPOSURE]: Analysis results and final articles are stored locally in the
reports/directory within the workspace. No evidence of unauthorized data transmission or exfiltration to third-party domains was found. - [PROMPT_INJECTION]: The skill processes external financial data, which presents a surface for indirect prompt injection (Category 8). However, the instructions focus on structured data extraction and verification using specialized tools, which mitigates the risk of the agent following instructions embedded in financial documents.
Audit Metadata