business-model-to-market
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input to populate business modeling frameworks and generate Excel workbooks, creating an indirect prompt injection surface.
- Ingestion points: User input provided during the business modeling interview, which is used to generate
answers.jsonin the workspace. - Boundary markers: Absent. The instructions do not define delimiters or specific warnings for the agent to ignore instructions potentially embedded within user-supplied business descriptions.
- Capability inventory: The skill utilizes
Bash,Read, andWritetools to execute a local Python script (build_gtm_workbook.py) for data processing and file generation. - Sanitization: The
build_gtm_workbook.pyscript performs standard JSON parsing but lacks specific content-level sanitization or escaping for strings before writing them into the output Excel workbook cells.
Audit Metadata