support-finance-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes well-known Python packages for data analysis and visualization, including pandas, numpy, matplotlib, and scipy.\n- [INDIRECT_PROMPT_INJECTION]: The skill's architecture involves ingesting untrusted financial data, which creates a susceptibility to indirect prompt injection.\n
- Ingestion points: External data enters the agent context through the
financial_dataSQL table and thehistorical_dataobject in the Python modules (SKILL.md).\n - Boundary markers: No specific delimiters or safety instructions are implemented to prevent the agent from following commands embedded in the data records.\n
- Capability inventory: The agent processes this data to generate risk assessments and strategic recommendations.\n
- Sanitization: The provided instructions and code snippets do not include input validation or sanitization for string fields in the ingested records.
Audit Metadata