finance-skills
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied financial data in JSON format through several Python scripts. The output from these scripts is then formatted into reports that the agent is instructed to interpret for executive summaries and decision support. This constitutes an indirect prompt injection surface where malicious instructions could be embedded in metadata fields (such as 'department names' or 'line item descriptions') within the input data. If the agent subsequently processes these generated reports, it may be influenced by the embedded malicious content.
- Ingestion points: Financial data files processed by scripts in
financial-analyst/scripts/andsaas-metrics-coach/scripts/. - Boundary markers: Absent. The skill instructions do not specify the use of delimiters or 'ignore' warnings for the data being analyzed.
- Capability inventory: The skill's scripts perform local mathematical processing and text reporting. They do not have capabilities for network access, file writing, or subprocess execution.
- Sanitization: String fields in the input data are not sanitized or escaped before being interpolated into the generated reports.
Audit Metadata