setup-kiple

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides integration instructions for a legitimate payment service (Kiple/kiplePay).
  • [EXTERNAL_DOWNLOADS]: The skill references official Kiple plugins and documentation hosted on GitHub within the vendor's organization (github.com/m2c/*) and official domains (kiple.com, kiplepay.com). These are legitimate vendor resources.
  • [COMMAND_EXECUTION]: Provides illustrative Python pseudo-code for signature calculation and constant-time verification for implementation by the user. There are no instructions for the agent to execute dynamic or untrusted code locally.
  • [CREDENTIALS_UNSAFE]: While the skill discusses the use of Merchant IDs and Secret Keys, it uses generic placeholders (e.g., <MERCHANT_ID>, MySecret) and includes critical rules advising the user to keep Secret Keys server-side and away from client-side scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill addresses the processing of external data (payment callbacks). It mitigates risks by instructing the agent to guide the user in implementing signature verification and secondary enquiry calls to the payment gateway before fulfilling orders.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 05:13 AM