business-growth-skills
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by design, as it requires the agent to ingest and analyze external JSON data files representing business entities.
- Ingestion points: Positional file arguments to Python scripts in the
customer-success-manager/scripts/,sales-engineer/scripts/, andrevenue-operations/scripts/directories. - Boundary markers: Not present. The scripts parse JSON data directly and the resulting analysis is presented to the agent without specific delimiters or instructions to ignore potential commands embedded within the data strings.
- Capability inventory: The skill's functionality relies on executing accompanying Python scripts via the shell. These scripts are limited to local file read operations and console output, with no network or write capabilities.
- Sanitization: The scripts utilize standard library JSON parsing which ensures structural validity but does not filter or sanitize the content of strings against natural language instruction injection.
Audit Metadata