dsh-auto-approval-plugin
Run the following command in DeepSeek Harness:
dsh plugin install StyxNether/dsh-auto-approval-plugin
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command `dsh plugin install StyxNether/dsh-auto-approval-plugin` with the full source address: https://github.com/StyxNether/dsh-auto-approval-plugin.
About this plugin
DeepSeek Harness users often grapple with balancing automation and security in permission management—manual approvals slow down workflows, while full access poses risks. The dsh-auto-approval-plugin introduces a smart intermediate tier that automatically approves harmless commands (e.g., read-only queries, simple text processing) and operations within configured trusted areas (like specific folders for reads/writes), reducing unnecessary interruptions. Its core capability lies in a real-time rule engine that classifies requests, approving only verified safe actions while deferring everything else to the user. This plugin is ideal for developers, testers, or administrators working in trusted environments, such as automated scripting or routine development, boosting productivity without compromising necessary controls or weakening security boundaries.
Use Cases
- Automatically execute git commands within trusted folders without manual confirmation.
- Automate daily file operations to enhance development workflow efficiency.
- Use for scripts and automated tasks to minimize user interruptions.
Best For
- Developers who frequently need to execute secure commands.
- System administrators seeking to balance security and efficiency.
- Test engineers looking to reduce approval steps in automated testing.
Related Plugins
A network security red-team benchmark plugin for DeepSeek-V4.1/Flash featuring dual-layer kernel injection and zero-tool architecture for controlled model safety assessment.
A security red-team prompt plugin for DeepSeek-V4 that uses code-formal mapping and zero-trigger system prompts to enable unconditional output, intended for authorized testing and research only.
Adds an Auto approval mode on the official workspace-write sandbox, classifying semantic risks, asking when ambiguous, and denying destructive operations.
Undo/rollback system for DSH: config & plugin snapshots, one-click undo/redo/restore, message-level revert, secret masking, safe mode, and offline WebUI/GUI/CLI rescue tools for when DSH won't start.