DSH Plugins Marketplace

DSH Plugins

Plugins

/

dsh-policy-drift-proof

d

dsh-policy-drift-proof

Manifest valid2

Content-addressed, value-redacted policy drift evidence for DeepSeek Harness

hasBundlePatch

dsh-policy-drift-proof

CI MIT license Node.js 22+ Awesome DSH Plugins

Read-only, content-addressed policy/configuration drift evidence for DeepSeek Harness.

Version 0.2 adds host-neutral DSH ToolDefinitions, a proof-only inline Codex MCP surface, real ToolRuntime calls and a stock Web Loader regression. The package exposes namespace exports only and does not bundle a second DSH runtime.

This plugin does not enforce tool calls, approve actions, scan repositories, or repair configuration. dsh-tool-policy already provides pre-execution policy routing, while SecurStack provides security scans and policy gates. This plugin covers the missing evidence question: did the policy snapshot actually observed by an operator differ from the pinned baseline, and was the difference weakening, tightening, exact, or unclassified?

Evidence model

The explicit manifest pins a baseline and observed policy-snapshot/v1 by SHA-256 and revision. Rules cover declared JSON Pointer roots:

  • ordered-not-weaker: enum order is restrictive to permissive; moving right fails.
  • set-no-additions: additions fail, removals are recorded as tightening.
  • exact: any change fails.
  • any changed covered leaf without a rule fails closed as UNCLASSIFIED_DRIFT.

Reports include paths, classifications and SHA-256 digests only. They never include policy values. Secret-shaped fields, raw output fields, absolute/escaping paths, symlinks, oversized inputs and excessive structure are rejected. The verifier performs no network calls or child processes and writes only one content-addressed JSON report beneath the explicit artifactDir, then reads it back and verifies its digest.

verified means both snapshot hashes and revisions matched and no weakening, exact or unclassified violation was found. Tightening remains observable through driftStatus: "changed". This is evidence about supplied snapshots, not a security certification.

CLI

node bin/dsh-policy-drift-proof.mjs inspect \
  --workspace examples/basic \
  --manifest policy-drift.manifest.json

node bin/dsh-policy-drift-proof.mjs verify \
  --workspace examples/basic \
  --manifest policy-drift.manifest.json \
  --artifactDir artifacts

The CLI prints one JSON object to stdout. A drift violation exits 2; invalid usage exits 1.

DeepSeek Harness bundle

dsh plugin --profile policy-proof add github:dongsheng123132/dsh-policy-drift-proof#<commit>
dsh profile --profile policy-proof compose

The bundle registers:

  • dsh_policy_drift_inspect
  • dsh_policy_drift_verify

The companion stdio MCP server exposes policy_drift_inspect and policy_drift_verify through .mcp.json. MCP accepts an inline manifest and pinned inline snapshots, performs no filesystem/network/subprocess/write operations, rejects secret- and raw-output-shaped fields, and never returns policy values. DSH and CLI remain the surfaces for workspace-bound files and content-addressed report publication.

Verification

npm test
npm run check
npm run smoke:plugin
npm run smoke:mcp
DSH_CHECKOUT=/path/to/built/deepseek-harness npm run smoke:dsh
DSH_CHECKOUT=/path/to/built/deepseek-harness DSH_HOME=/path/to/isolated-home npm run smoke:web-loader
python C:/Users/ZhuanZ/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py .

CI runs tests, structural checks and MCP smoke on Ubuntu and Windows. Node.js 22 or newer is required.

License

MIT

Comments

Loading…

From the same category

api-relay-audit

by toby-bridges

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Security & AuditDevelopment & InfrastructureManifest valid

854

AGPL-3.0

Python

Sep 16, 2026

dsh plugin --profile web add dsh-api-relay-audit

by sandbaseai

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

Security & AuditWorkflow & AutomationManifest valid

649

8/wk

Apache-2.0

TypeScript

Sep 22, 2026

dsh plugin --profile web add managed-agents

by hashgraph-online

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Security & AuditTools & CapabilitiesManifest valid

645

Apache-2.0

Python

Sep 22, 2026

Index only — not installable

by SeaOf0

基于dsh web实现的多种模式,目的是服务于redteam进行授权的安全研究,覆盖渗透测试、红队评估、代码审计等范围领域,请勿用于非法行为。(允许二开,赋予模块各位自己的业务逻辑,方法论只有自己熟练的才好用,好的方法论=好的生态)

Tools & CapabilitiesSecurity & AuditModels & ProvidersTerminal & ClientsManifest valid

565

MIT

Python

Sep 22, 2026

dsh plugin --profile web add @dsh-external/dsh-redteam-model

by howmp

面向 DeepSeek Harness(dsh)的渗透测试模式 @CloverSecLabs

Tools & CapabilitiesSecurity & AuditTerminal & ClientsManifest valid

527

JavaScript

Sep 11, 2026

dsh plugin --profile web add @howmp/dsh-pentest

by xiaods

k8e.sh - OpenSource Agentic AI Sandbox Matrix

Security & AuditTools & CapabilitiesManifest valid

496

17/wk

Apache-2.0

Go

Sep 22, 2026

dsh plugin --profile web add @k8e-sandbox/dsh-k8e-sandbox-bundle