setup-payments
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Mentions the requirement for the @kelviq/mcp-server Node.js package as part of the initial setup. This is a vendor-owned resource.
- [COMMAND_EXECUTION]: Uses various kelviq: MCP tools (e.g., checkout_create_session, subscription_cancel) to handle billing and account management. These tools are used for their intended purpose within the agent context.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: Untrusted data enters via kelviq:subscription_list and kelviq:docs_read in SKILL.md. Boundary markers: Absent. Capability inventory: Subprocess calls are possible through the kelviq: MCP tools in SKILL.md which allow state changes (update/cancel). Sanitization: Absent. The risk is mitigated by explicit instructions to seek user confirmation before destructive actions.
Audit Metadata