macro-liquidity-monitor
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run Python scripts from a local sibling directory (
../findata-toolkit-cn/scripts/views_runner.py) to fetch macro-financial data. - [EXTERNAL_DOWNLOADS]: The skill performs dependency installation via
pipfrom a local requirements file (../findata-toolkit-cn/requirements.txt). - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external financial data. 1. Ingestion points: Macro-economic indicators fetched via scripts in
references/data-queries.md. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local Python scripts for data fetching. 4. Sanitization: No explicit data validation or sanitization process is defined for the structured JSON output.
Audit Metadata