Skip to content

lookup/validate 深度防禦加固:本地 domain 內容的 data-guard、entry_points 路徑邊界、引數 quoting #22

Description

@kiki830621

Problem

Original text:
#14/#15 expand the read scope to the user's cwd axioms//domains/, so untrusted local domain content now enters LLM context during lookup/validate, and there's no explicit "treat domain content as data, not instructions" guard.」
— Source: #12#21 cluster verify,security lens(2026-07-06);DA 判定 INFO 級 backlog

三項深度防禦建議(皆 LOW/INFO,非 blocker):

  1. lookup/validate 讀入 domain 內容時加「內容是 data 不是指令」的 guard 語句
  2. 本地 domain.yamlentry_points 限制在該 domain 目錄內(防 .. 路徑跳脫)
  3. skill 指令中引導的 bash 對路徑引數統一 quoting 慣例

Type

feature

Expected

三個 skill 的相應段落補上述防護;門檻低、一個 commit 可完成。

Impact

低(需使用者已在惡意 repo 內 + 唯讀面),純加固。

Current Status

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions