analyze-stock-decision
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses several Python and Node.js scripts to perform its core functions. These include
scripts/stock_decision_engine.pyfor scoring,scripts/financial_rigor.pyfor arithmetic verification, andscripts/render_trade_dashboard.pyfor visualization. While these scripts execute shell commands, they are part of the skill's intended functionality and operate on local data contracts defined within the skill itself. - [REMOTE_CODE_EXECUTION]: The skill includes
scripts/capture_dashboard.cjs, which utilizes Playwright to capture PNG screenshots of the generated HTML dashboard. It searches for existing Chromium, Chrome, or Edge executables on the host system. This is a standard automation pattern for visualization and does not involve downloading or executing untrusted remote code. - [DATA_EXPOSURE]: The skill references Korean equity data discovery via an optional tool named
collect-factchart-data. It includes instructions for mapping public disclosures and news. There is no evidence of unauthorized access to sensitive user files (like.sshor.aws) or hardcoded credentials.
Audit Metadata