fixed-income-weekly-brief
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
finxcommand-line utility to interface with thegildata-aidatafinancial database. This is a legitimate functional requirement for fetching market indicators like interest rates and bond yields as part of the report generation process.\n- [EXTERNAL_DOWNLOADS]: Market data and macro news summaries are fetched from professional financial data providers. These operations are limited to data retrieval and do not involve downloading or executing external scripts from untrusted sources.\n- [SAFE]: Indirect prompt injection risks were evaluated for the news ingestion components (MacroNewslist,NewsInfoList). 1. Ingestion points: Automated news summaries inSKILL.md. 2. Boundary markers: Structured markdown headers in the output template. 3. Capability inventory: Data retrieval tools (finx,time). 4. Sanitization: Not explicitly defined, but risk is inherently low given the restricted scope of data tools and summarization-only behavior.\n- [SAFE]: No instances of prompt injection, obfuscation, hardcoded credentials, or persistence mechanisms were found. The skill operates entirely within the scope of its stated purpose for financial research.
Audit Metadata