免費插件,適用於 Claude 程式碼 與 Codex:阻止提示詞與代理讀取的檔案中洩漏機密,於送達模型前將其移除。實際呼叫仍會取得值。
AI 翻譯
Free plugin for Claude Code and Codex: stops secrets in prompts and in files the agent reads before they reach the model. Real calls still get the value.
外掛Python · ShellGitHub @Mcpgate-de上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證Keeps secrets and PII out of the cloud model. Hook plugin for Claude Code/Codex with a local vault.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
An AI agent sees what you type and what its tools print: passwords, tokens, a
customer's e-mail address. maisecrets intercepts detected secrets and personal
data before they reach the cloud model. The real value goes back in only where
the call happens, and the model never sees it there either. By default
maisecrets adds no approval of its own: in Claude Code your permission rules
decide, as before; in Codex maisecrets answers allow, and Codex's sandbox and
its approval of MCP tools still apply. maisecrets itself sends no
prompt, value or telemetry to a server.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
An AI agent sees what you type and what its tools print: passwords, tokens, a
customer's e-mail address. maisecrets intercepts detected secrets and personal
data before they reach the cloud model. The real value goes back in only where
the call happens, and the model never sees it there either. By default
maisecrets adds no approval of its own: in Claude Code your permission rules
decide, as before; in Codex maisecrets answers allow, and Codex's sandbox and
its approval of MCP tools still apply. maisecrets itself sends no
prompt, value or telemetry to a server.檢視完整 README ↗