obsidian-plugin/algometrix_second_brain_builder
1
0
Fork 0
mirror of https://github.com/algometrix/second_brain_builder.git synced 2026-07-22 08:29:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Document shell-execution mitigations in a README Security section

Browse source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
algometrix 2026-07-15 14:18:29 -04:00
parent f4352433d2
commit 7fa1f80372
1 changed files with 9 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
README.md
View file

@ -306,6 +306,15 @@ Run `fix-all.js` without `--fix` after a large batch generation, or when a merma
The selected text and surrounding note content are sent to whichever backend you configure. With Claude, Gemini, or Codex, that means the respective cloud API, under your own account and their terms. With Ollama, everything stays on your machine. The plugin itself collects nothing.
## Security
The plugin spawns the AI CLI you configure, which is why Obsidian shows a "shell execution" notice for it. The design limits what that process can do:
- Note content is passed to the CLI via stdin, never interpolated into a shell command line.
- Each CLI runs in a restricted mode: Claude with `--disallowedTools` (no file edits, no shell), Gemini with `--approval-mode plan`, Codex with `--sandbox read-only`.
- Only the executable path and model name from your own settings are used to build the command; the plugin never runs commands supplied by note content or by the model's output.
- All generated content is written through Obsidian's vault API, not directly to disk.
## Development
```bash