business-growth-skills
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and analysis of external business data (such as RFP requirements, customer usage metrics, and sales pipeline details) provided in JSON format. The agent is then guided to interpret the output of Python scripts to generate summaries, strategic plans, and recommendations. This workflow introduces an attack surface for indirect prompt injection, where malicious instructions embedded in the source data could potentially influence the agent's behavior during report generation.
- Ingestion points: Scripts located in customer-success-manager/scripts/, sales-engineer/scripts/, and revenue-operations/scripts/ all process external JSON files.
- Boundary markers: No explicit delimiters or instructions are used to distinguish untrusted data from the system prompt during the analysis phase.
- Capability inventory: The agent executes shell commands to run Python tools and interprets the resulting data to formulate business documents and responses.
- Sanitization: The skill lacks explicit sanitization or validation logic for the textual content within the ingested JSON files.
Audit Metadata