usage-based-billing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes official vendor-owned Node.js packages (
@kelviq/mcp-server) and follows industry-standard practices for managing API keys through environment variables or MCP configuration. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as customer identifiers and license keys which are interpolated into tool calls. While this is an entry point for untrusted data, it is the primary purpose of the skill and no dangerous patterns were detected.
- Ingestion points: User-provided
customerId,featureId, and license keys processed by the agent. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: File system access and network operations are restricted to the
kelviq:MCP tool suite for usage reporting and entitlement retrieval. - Sanitization: Not specified in the instructions; standard LLM and MCP tool guardrails apply.
Audit Metadata