Plugin directory / Developer / noatmark-dsh-plugin
noatmark-dsh-plugin
Verified · install-tested on dsh ylwl1997
What it does
Text hygiene as a dsh plugin: sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
Works — verified, early-stage project
Text hygiene as a dsh plugin: sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection. It installs cleanly and boots without issues in our testing. It's early-stage but functional.
“Verified” means our automated CI actually ran dsh plugin add in a clean profile and it booted — nothing more. Feature descriptions and version compatibility are the author’s claims. This is not a security audit and not an endorsement of third-party code.
README
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
| Tool | What it does |
|---|---|
sanitize_text |
Strip invisible/zero-width characters and flag prompt-injection + hidden-text signals. |
scan_text |
Report invisible characters (with code points + positions), injection patterns, and hidden text. |
clean_format |
Clean LLM formatting artifacts (blank lines, stray fences, trailing spaces) — meaning untouched. |
sanitize_csv |
Escape 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
Install
Install the catalog once, then DeepSeek Harness can find and install any plugin from this site automatically:
dsh plugin add dshbase-catalogThen say "install noatmark-dsh-plugin for me" — your agent finds it in the directory and installs it. Docs: dshbase-catalog · verified packs.
Web profile:
dsh plugin --profile web add noatmark-dsh-pluginHeadless (CLI) profile:
dsh plugin --profile headless add noatmark-dsh-pluginPackage
npm: noatmark-dsh-plugin · version 0.1.0 · tested on dsh 0.1.0-rc.6
Test report
Verified end-to-end: L1 install + L2 load + L3 runtime Q&A on dsh 0.1.0-rc.6.
When to use it
Sanitize untrusted text, scan for invisible characters, clean LLM formatting, and escape CSV — hygiene before content touches the model.
Who it's for
Users who paste text from the web or untrusted sources and want zero-width/invisible-character attacks caught first.
For developers — extending it
Add hygiene rules and detectors — new invisible-character ranges, formatting normalizers, and sanitizer presets.
Share this badge
Drop this badge into your README — it links back here and updates automatically when our test status changes:
[](https://dshbase.com/plugins/noatmark-dsh-plugin/)<a href="https://dshbase.com/plugins/noatmark-dsh-plugin/"><img src="https://dshbase.com/badges/noatmark-dsh-plugin.svg" alt="dshbase install-tested"></a>