dsh-blame-avoid
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-blame-avoid
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-blame-avoid in DeepSeek Harness to install this plugin; the source repository is https://github.com/uckkk/dsh-blame-avoid.
About this plugin
In many admin workflows, the most stressful part is rarely the command itself but the question of who takes the blame when something goes wrong. dsh-blame-avoid tackles exactly that pain point: it registers a tool called blame_avoid that, when invoked in a session with the relevant parameters, returns a set of structured risk-mitigation and responsibility-boundary suggestions, helping you flag potential liability before you press enter.
The implementation is intentionally lightweight—written in pure Node.js with zero external dependencies and no network calls whatsoever. That means it runs entirely offline, never ships sensitive parameters to a remote service, and works comfortably in air-gapped or intranet environments.
Whether you are a sysadmin, a DevOps engineer, or any technician who needs a quick pre-flight check on risk points and ownership boundaries before executing an admin operation, this plugin gives you a zero-config, local helper that adds a layer of deliberate thinking before action.
Use Cases
- Reviewing responsibility boundaries before executing high-risk admin commands
- Running local risk assessments in intranet or air-gapped environments
- Embedding a pre-action risk check into team operational checklists
Best For
- Sysadmins and DevOps engineers
- Technicians running admin operations in offline environments
- Security teams focused on compliance and accountability
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.