service-estimate-generator
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (job details, customer names, service descriptions) to generate estimate documents, creating an indirect prompt injection surface.
- Ingestion points: User-supplied service descriptions, business contact blocks, and pricing details ingested via conversation.
- Boundary markers: The instructions do not specify explicit delimiters for user content, but do recommend an 'AI scope draft' to organize details.
- Capability inventory: The skill uses tools (
set_estimate_details,set_estimate_prices,draft_estimate) to write data to an external service (doany.ai) and generate PDF previews. - Sanitization: The skill explicitly instructs the agent to 'Verify pricing and text separately before opening the PDF preview', providing a human-in-the-loop verification step.
Audit Metadata