dsh-provenance
Pre-install supply-chain checks for DeepSeek Harness plugins: verify the tarball you are about to install matches the source you read, before any code runs.
为 DeepSeek Harness 插件做安装前供应链校验：在代码运行前核对即将安装的包是否与你读到的源码一致。
How to install
dsh plugin add dsh-provenance About
dsh-provenance English | 中文 **The source you read on GitHub is not necessarily the package you install.** A supply-chain preflight for DeepSeek Harness plugins. It answers a question no other scanner in this ecosystem asks. Existing plugin scanners read the files already on your disk and ask *"does this code do something bad?"*. That is a useful question, but it comes second. The first question is: **Is this code the code the author showed me?** An npm tarball is whatever the publisher uploaded. The registry does not build it from the repository, and nothing forces the two to agree. A publishe…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-08-19
- Created
- 2026-08-17
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin, dsh-plugin-market, dsh-plugin-verify, dsh-plugins
Related plugins
dsh-auto-review
PerryLink/dsh-auto-review
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.
dsh-passwords
slywalker2006/dsh-passwords
Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.
dsh-auth-gate
TecFancy/dsh-auth-gate
Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).
dsh-approval-llm
Letter2025/dsh-approval-llm
Model-based permission approval: an approval-request answerer backed by a separate reviewer model.