Aider 因自动加载仓库配置执行 shell 获评高危 CVE
MODEL 杂志梳理 CVE-2026-115726(VulnCheck 评 8.5 高危):Aider 至 0.86.2 会无信任提示自动加载仓库根目录 .aider.conf.yml,其中 notifications-command 与 editor 经 shell=True 执行,克隆恶意仓库后一条消息即可跑命令。
编程智能体辅助写补丁时,信任边界往往不在 diff 里。MODEL 杂志报道,Aider 收到 CVE-2026-115726(VulnCheck 于 10 月 23 日按 CVSS 4.0 评为 8.5 高危):直至 0.86.2,工具会无信任提示自动加载仓库根目录的 .aider.conf.yml;其中 notifications-command 与 editor 两个键会直接进入 subprocess 且 shell=True。克隆被植入配置的仓库、启动 Aider 并发送一条消息后,仓库里的命令会以当前用户身份执行,且绕过模型建议命令时的确认流程。
git blame 显示两处 sink 的作者标记为 “Paul Gauthier (aider)”,文档称该标记表示由 Aider 在人类驾驶下写出。加入 notifications-command 的 v0.76.0 发行说明写有「本版本 85% 代码由 Aider 编写」;随后一次人工提交去掉了 editor 调用中的引号。截至报道日,相关 GitHub issue(约 10 月 20 日提交)仍开放、无评论、无修复,主干最近提交停在 5 月 22 日。
作者观点强调:问题不在 shell=True 本身,而在「本该来自你本机的字符串」可以来自刚克隆的陌生人仓库。操作建议是:在不信任的仓库里先读配置文件,更好是在容器中运行编程智能体。本稿未复现漏洞;是否已有补丁以官方仓库与 CVE 记录为准。
Aider CVE: coding agent wrote its own shell=True
Aider just got a CVE for running shell commands from a file in someone else's repo. We read the git history. Both shell=True lines it runs through were written by Aider itself.
• CVE-2026-115726, rated 8.5 High by VulnCheck on Oct 23. Every Aider version through 0.86.2 is affected. • Aider auto-loads .aider.conf.yml from the repo root with no trust prompt. Two keys, notifications-command and editor, go straight to subprocess with shell=True. • Clone a booby-trapped repo, start Aider, send one message, and the repo's command runs as you. It skips the confirmation Aider uses for commands the model suggests. • git blame at v0.86.2: both sinks are authored by "Paul Gauthier (aider)". Aider's docs say that tag means Aider wrote the change. • The release that added notifications-command, v0.76.0: "Aider wrote 85% of the code in this release." • The catch: Aider's version of the editor call quoted the command. An hour later a human commit dropped the quoting. Human and agent each did half. • The GitHub issue was filed Oct 20. As of today: open, 0 comments, no fix. Last commit to main was May 22.
Our take: shell=True on a command you typed is a feature. The bug is that the string can come from a stranger's repo, and no commit or review asked where it comes from. Coding agents write the diff they're asked for. Trust boundaries are never in the diff.
Takeaway: before running any coding agent in a repo you didn't write, read its config files. Better, run it in a container.
#AIcoding
— MODEL Editors