You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
**Description:** "When enabled, Roo will automatically view directory contents and read files without requiring you to click the Approve button."
74
74
75
-
**Risk level:**Low
75
+
**Risk level:**Medium
76
76
77
-
This is the safest auto-approval setting as it only gives Roo the ability to read files, not modify them. Recommended as a starting point for most users, even in production environments.
77
+
While this setting only allows reading files (not modifying them), it could potentially expose sensitive data. Still recommended as a starting point for most users, but be mindful of what files Roo can access.
78
78
:::
79
79
80
80
### Write Operations
@@ -199,7 +199,7 @@ Enables Roo to create and complete subtasks automatically. This relates to workf
199
199
200
200
### Command Execution
201
201
202
-
:::danger Command Execution
202
+
:::caution Command Execution
203
203
<imgsrc="/img/auto-approving-actions/auto-approving-actions-13.png"alt="Command execution setting with whitelist interface"width="550" />
@@ -208,9 +208,9 @@ Enables Roo to create and complete subtasks automatically. This relates to workf
208
208
209
209
**Command management:** "Command prefixes that can be auto-executed when 'Always approve execute operations' is enabled. Add * to allow all commands (use with caution)."
210
210
211
-
**Risk level:**Very High
211
+
**Risk level:** High
212
212
213
-
This is the highest-risk setting as it allows terminal command execution. Critical security features:
213
+
This setting allows terminal command execution with controls. While risky, the whitelist feature limits what commands can run. Important security features:
214
214
215
215
- Whitelist specific command prefixes (recommended)
216
216
- Never use * wildcard in production or with sensitive data
0 commit comments