Sentinel Vault: Runs on Atlassian AI apps

Описание и применение

Sentinel Vault использует Atlassian Forge LLMs API для проверки контента Confluence без внешних ключей и исходящего трафика. В продакшн‑версии приложение соответствует требованиям Runs on Atlassian, но в дев‑версии возможен исходящий трафик через веб‑триггер. AI‑обзор отключён по умолчанию и активируется только администратором, а токены оплачиваются учётной записью разработчика Forge.

Задача

Confluence admins must decide whether to enable AI review in Sentinel Vault, but the marketing claim of no external data egress and no API key may be misleading without code verification.

Результат

The app satisfies the Runs on Atlassian badge requirements in production, but the development build can egress data via a web trigger. AI review is disabled by default and requires admin activation; token usage is billed to the vendor’s Forge account.

Рабочий процесс

• 1. Review the app’s manifest.yml for external permissions and modules.
• 2. Run forge eligibility on production and development builds to check Runs on Atlassian eligibility.
• 3. Inspect the deployment script scripts/deploy-prod.sh to confirm removal of dev modules.
• 4. Examine default configuration in logic.js to verify AI is off by default.
• 5. Verify that only admins can trigger AI reviews and that token usage is billed to the vendor’s Forge account.

Доказательства

Sentinel Vault is one of the Runs on Atlassian apps that review Confluence content with AI, through the Forge LLMs API, with no API key to paste and no external data egress declared.

Источник

$ forge eligibility -e production The version of your app [6.5.0] that's deployed to [production] is eligible for the Runs on Atlassian program.

Источник

$ forge eligibility -e development The version of your app [8.98.0] that's deployed to [development] is not eligible for the Runs on Atlassian program. - App is using a webtrigger module that can egress data

Источник

The default configuration in logic.js sets the validation engine's master switch to enabled: false. AI has its own switch, ai: { enabled: false, ... }

Источник

Token costs bill to the app vendor's Forge bill, so we enforce a Haiku-only policy (see isForgeLlmModelAllowed) at every layer.

Источник