dshplugin.devDeepSeek Harness Plugins
noatmark-dsh-plugin plugin logo
DeepSeek Harness Plugin

noatmark-dsh-plugin

1
Published by ylwl1997

NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV injection.

Modelsdsh-plugin

Get this plugin

Review the source, then continue to the publisher.

Get this plugin
Share on X ↗

About this plugin

Source snapshot 8/14/2026

noatmark-dsh-plugin

NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin.

Everything-is-a-plugin: this plugin gives your dsh agent four text-hygiene tools, backed by the same deterministic engines behind noatmark.com.

Tools

ToolWhat it does
sanitize_textStrip invisible/zero-width characters and flag prompt-injection + hidden-text signals.
scan_textReport invisible characters (with code points + positions), injection patterns, and hidden text.
clean_formatClean LLM formatting artifacts (blank lines, stray fences, trailing spaces) — meaning untouched.
sanitize_csvEscape CSV formula injection (OWASP): = + - @ prefixes get a leading quote.

All processing is deterministic and local — no data leaves your machine.

Install

Add this plugin to your dsh Web UI. If you're running from a source checkout, use a cordis.yml patch:

- insert:
    - id: noatmark
      name: noatmark-dsh-plugin

or point at the source directly (absolute path):

- insert:
    - id: noatmark
      name: '/path/to/noatmark-dsh-plugin/src/index.ts'

Start dsh with the patch:

npx @deepseek-ai/dsh web --patch ./cordis.yml

Usage

In a dsh session, ask the agent to use a tool, e.g.:

Sanitize this pasted text before you summarize it.

Scan this file for invisible characters.

Clean the formatting of this AI output.

Escape this CSV before saving it.

Development

pnpm install
pnpm build   # tsc -> dist/

Resources

  • Web tools: https://noatmark.com/
  • NoAtMark SDK (npm/PyPI): noatmark-text-hygiene
  • DeepSeek Harness: https://github.com/deepseek-ai/deepseek-harness
  • Official docs: https://deepseek-harness.github.io/deepseek-harness/

MIT