skills/tiun-app/skills/tiun-sdk/Gen Agent Trust Hub

tiun-sdk

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the tiun platform's SDKs and related dependencies from NPM, such as @tiun/sdk and @tiun/react-native-sdk. These are official vendor packages required for the skill's primary purpose.
  • [COMMAND_EXECUTION]: The instructions include standard development commands for package management (npm install, pnpm add, yarn add, pod install) and a quickstart installation command npx skills add tiun-app/skills. These commands are routine for setting up the development environment for the SDK.
  • [DATA_EXPOSURE]: The skill provides clear security guidance regarding sensitive information. It differentiates between the snippetId (a public identifier) and the X-TIUN-API-KEY (a server-side secret). It correctly instructs users to manage these via standard environment variable patterns and warns against exposing the API key to the client-side.
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes a Model Context Protocol (MCP) server (https://mcp.tiun.business/) to provide the agent with real-time metadata about a user's account configuration. While this represents an ingestion of external data, the skill includes explicit safety rules requiring the agent to obtain user confirmation before performing any write operations to the account, mitigating the risk of unauthorized changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 09:18 AM