Security & governancePlugin
Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys
Structure check pending
ai-agentchatgptclaudecodex
Back to Marketplace
Security & governancePlugin
dsh-sandbox-escalation-fix
JUSTMONIKA2022/dsh-sandbox-escalation-fix
dsh-sandbox-escalation-fix is a tool for DeepSeek Harness. Session-aware sandbox escalation compatibility plugin for DeepSeek Harness/DSH third-party model session sandbox escalation compatibility plugin
- Stars
- 49
- Forks
- 8
- Issues
- 1
- Update
- 45 days
REVIEW SCORECARD
Review Scorecard
7.7/10Average
License compliance9.0
Engineering quality6.8
Content completeness6.0
Repository scale7.0
Maintenance activity8.0
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Worth AI Review
7.8/10Consider
A focused, actively maintained compatibility fix for a real DSH sandbox escalation bug, but install only if you reproduc
Code quality8
README states all 40 tests and the TypeScript build pass against real Agent, ToolRuntime, Session, and Sandbox contracts, and describes fail-closed validation for malformed or mixed manifests.
Security7
The plugin is MIT-licensed, claims not to modify DSH core packages, and the README documents no download-and-execute or credential handling, but no independent audit or source review is visible.
Utility9
It targets concrete, quoted DSH errors (invalid justification, non-strictly-wider escalation, retry loops) that block third-party models like GPT from calling bash, pwsh, write, and edit under All Access.
Maintenance8
Last updated 2026-08-23 with explicit compatibility tracking through DSH 0.1.5-rc.2 and Desktop 2.0.3, and the repo is not archived.
Documentation7
The README is extensive with compatibility tables, before/after, and multiple install paths, but the install command is listed as unknown and the excerpt is truncated mid-section.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
PROJECT READMEREADMEExpandCollapse
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is dsh-sandbox-escalation-fix used for?
Session-aware sandbox escalation compatibility plugin for DeepSeek Harness/DSH third-party model session sandbox escalation compatibility plugin
How popular is dsh-sandbox-escalation-fix?
dsh-sandbox-escalation-fix has 49 stars and 8 forks on GitHub, last updated 2026-09-06.
What license does dsh-sandbox-escalation-fix use?
dsh-sandbox-escalation-fix is distributed under the MIT license.
Is dsh-sandbox-escalation-fix compatible with DeepSeek Harness?
dsh-sandbox-escalation-fix is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
Classification evidence
Project typePlugin
Feature categorySecurity & governance
Rule confidenceHigh
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:sandbox-escalation。
Security & governancePlugin
dsh-codex-subscription
WSL043
Connect your ChatGPT / Codex subscription to DeepSeek Harness: OAuth, models, quota, search and image generation, no API Key or Codex CLI needed.
Structure check pending
ai-agentchatgptchatgpt-pluschatgpt-pro
Security & governancePlugin
dsh-auto-review
PerryLink
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
Structure check pending
ai-safetyapprovalauto-reviewcordis
Security & governancePlugin
dsh-permission-rules
PerryLink
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
Structure check pending
ai-safetyallow-deny-askapprovalcordis
Security & governancePlugin
dsh-win32
sjh9714
Fix and diagnose DeepSeek Harness on native Windows. Official PowerShell, Workspace Write, shortcuts, and legacy preset repair. No WSL.
Structure check pending
ai-agentdeepseekdeepseek-harnessdeepseek-harness-plugin
Security & governancePlugin
dsh-reverse-skill
dhicoc
Complete reverse-skill (85 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.
Structure check pending
ctfdeepseek-harnessdsh-pluginpentest