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-reverse-skill
dhicoc/dsh-reverse-skill
dsh-reverse-skill is a tool for DeepSeek Harness. Complete reverse-skill (85 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.
- Stars
- 80
- Forks
- 11
- Issues
- 1
- Update
- 42 days
REVIEW SCORECARD
Review Scorecard
7.8/10Average
License compliance9.0
Engineering quality6.9
Content completeness7.0
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
Well-engineered dsh wrapper bundling 87 reverse-engineering skills, but only useful for authorized security work.
Code quality8
README documents a data-driven recursive scanner, a re-runnable `npm test` asserting all 87 skills register and get() non-empty, plus a BOM/CRLF fixture test and a pre-publish CI check.
Security7
The plugin only bundles static SKILL.md files with no download-and-execute or credential handling shown, but it ships offensive pentest/reverse-engineering tooling and the README notes `allowed-tools`/`disallowed-tools` are not enforced by dsh.
Utility8
It packages the full 27k-star upstream reverse-skill set (87 SKILL.md) into a one-command dsh plugin, solving the real pain of manually maintaining a skill candidate list for CTF and pentest workflows.
Maintenance8
Last updated 2026-08-22, not archived, and the README describes an automated publish workflow running the same test suite before `npm publish`.
Documentation8
README covers install, build, plugin vs preset fallback, discovery priority, working principle, verification, and an explicit 'known limitations' section, though some config key names are flagged as version-dependent.
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 repositoryINSTALL REFERENCE
Install reference
dsh plugin --profile web add github:dhicoc/dsh-reverse-skillThis command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.
PROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is dsh-reverse-skill used for?
Complete reverse-skill (85 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.
How popular is dsh-reverse-skill?
dsh-reverse-skill has 80 stars and 11 forks on GitHub, last updated 2026-08-22.
What license does dsh-reverse-skill use?
dsh-reverse-skill is distributed under the MIT license.
Is dsh-reverse-skill compatible with DeepSeek Harness?
dsh-reverse-skill 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:security。
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-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-oauthchatgpt-plus
Security & governancePlugin
dockyard-dsh
AITabby
A macOS-only native account-pool and provider plugin for DeepSeek Harness.
Structure check pending
account-pooldeepseek-harnessdsh-pluginmacos
Security & governanceInfrastructure
axern
cofy-x
Open-source sandboxes for AI agents, untrusted code execution, and durable services.
Outside plugin validation
agent-sandboxagentic-infrastructureai-agentscloud-native