Security & PermissionsDeepSeek Harness plugin

dsh-Almost_Full_Access

Name: dsh-Almost_Full_Access
Author: Alnita-M

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

License: MIT
Added: 2026-08-19

GitHub info

License: MIT
Primary language: JavaScript
Last push: Aug 18, 2026, 2:43 PM
Maintainer: Alnita-M
Added: 2026-08-19

Install

Install command

dsh plugin --profile web add dsh-almost-full-access

README badge

Add this Markdown to your plugin README to link back to its listing.

Listed onDSH Get

[![Listed on DSH Get](https://img.shields.io/badge/Listed_on-DSH_Get-1677ff?style=flat-square)](https://dshget.com/plugins/Alnita-M/dsh-Almost_Full_Access)

Security & Permissions

api-relay-audit

★ 819

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Security & Permissionstoby-bridges

dsh-pentest

★ 324

Authorized pentest mode for DeepSeek Harness — exploration chain, assets and findings with a Web view.

Security & Permissionshowmp

dsh-auto-review

★ 120

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

Security & PermissionsPerryLink