chendengyuanxm/dsh-plugin-security-audit

chendengyuanxm★ 0JavaScript最后同步: 2026-08-15

在 GitHub 打开

Static security audit for dynamic Cordis plugins in DeepSeek Harness (DSH): rule-based source scanning, risk reports injected into tool results, and user-approval escalation before activating high-risk plugin packages. 动态 Cordis 插件静态安全审查。

README 摘要

dsh-plugin-security-audit Static security audit for dynamic Cordis plugins in DeepSeek Harness (DSH). English · 中文 What it does Dynamic Cordis plugins defined in a DSH session run plain JavaScript with access to real Host services — files, shell, sessions, credentials. The sandbox restricts accidental misuse; it is not a security boundary against malicious code. This plugin adds a deterministic, zero-token static audit layer over every cordis define / cordis run call in the session: - Scan on define — every cordis define 's code.host / code.client source is scanned by a 16-rule engine before the package is minted. - Gate on activate — a cordis run for a package with critical or high findings is escalated to a user approval ( {kind:'ask'} ) whose reason carries the top findings. Clean and low-risk packages run normally. - Report in the conversation — a compact risk report is appended beside every cordis define / cordis run result as an additionalContexts notice, so both the model and the user see it in the tool-result stream. - Fail-open by design — any internal scan error is logged and the audited call proceeds untouched. The audit layer itself is never a failure point for the harn…

在 GitHub 查看完整 README →
工具/开发cordisdeepseek-harnessdshdsh-pluginsecurity-auditstatic-analysis

分类