setup-payments

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill integrates external data that could serve as a vector for indirect prompt injection.
  • Ingestion points: The skill fetches external documentation via the kelviq:docs_read tool and processes caller-defined data such as metadata, discountCode, and customerId (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill when processing this external content.
  • Capability inventory: The skill has the ability to perform network operations (creating checkout sessions), manage financial records (creating/updating subscriptions), and perform destructive actions (canceling subscriptions).
  • Sanitization: There are no documented sanitization or validation steps for the data retrieved from documentation or provided by the user before it is used in subsequent tool calls.
  • [EXTERNAL_DOWNLOADS]: The skill references the @kelviq/mcp-server Node.js package. This is an official resource provided by the skill's author for interacting with their platform services (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 12:10 PM