概览
dsh-context-provenance
社区 · Topic 自动分析 — 通过 GitHub dsh-plugin Topic 自动发现。静态检查在不执行第三方代码的前提下，验证了固定公开版本的根目录 bundle 契约与已提交文件；这不等于人工审核、安全审计、运行时冒烟测试、发布者身份验证或官方背书。
从 GitHub 安装此组合包
CLI 会验证组合包、调用原生 DSH 安装，成功后才上报完成。
npx dshpub add 030611/dsh-context-provenance --ref 3788ecbbdf9391d8ab0c29a18ed65bd59ca1c30f能力
它贡献了什么
README / ZH
插件文档
An observe-only, CPU-only, local-only DeepSeek Harness plugin that reports what public runtime interfaces can actually prove about the requesting Agent's context. It retains only the two most recent ordinary agent-loop request observations in memory and exposes them through the existing Cordis inspect query mechanism. It performs no file, network, subprocess, GPU, persistence, session, permission, tool, model-routing, or request mutation.
LIMITATIONS
已知限制
- Loader entries do not identify the bundle, profile, override, or dependency that introduced them. - Plugin inventory reveals ordered enablement and lifecycle categories, but never raw entry ids, package names, file URLs, absolute paths, or patch specifiers. - A tool name or schema does not identify its owning plugin. - Skill names remain visible because they are the public callable identity; source/provider are reduced to fixed categories. A skill name itself may still be sensitive if a deployment chooses a sensitive name. - AGENTS location categories are durable injected-source metadata, not a filesystem inventory or proof of hidden instructions. - Adjacent observations cover actual ordinary `llm/stream` calls seen while this plugin is mounted. Earlier requests, auxiliary calls, and observations lost on unload or restart are unavailable.