@58catmiao/dsh-sciwork

dsh-sciwork 把「科研模式」装进 DeepSeek Harness：一个落在自己硬盘上的科研库、一套技能与一块面板。工作台默认打开（页头、指标条、跨课题待办、概览仪表、快速登记），可一键切回七页签旧面板；课题、图、草稿、文献、数据表、期刊档案、投稿台账各有其位，写入经库脚本落盘并登记，面板只读为主、自己不出图。技能把「怎么画、怎么写、怎么引」固化成纪律，外加 12 份期刊档案兜底。零 npm 依赖，路径运行时解析。

PluginDeveloperDesktopData

Verification

L4 · Install tested

Failed

Risk

LowRisk

Health

Active

Trust

Silver

Install verification: sandbox install ok, web smoke failed (L5) · tested on dsh 0.2.1-rc.2 · last checked 10-19Install verification details →

What it doesAI

dsh-sciwork 把「科研模式」装进 DeepSeek Harness：一个落在自己硬盘上的科研库、一套技能与一块面板。课题、图、草稿、文献、数据表、期刊档案、投稿台账各有其位，写入都经库脚本落盘并登记，面板只读为主、自己不出图。技能把「怎么画、怎么写、怎么引」固化成纪律：出图交给 Origin 链路，写作、引用、投稿格式各有专门技能，外加 12 份期刊档案兜底。零 npm 依赖，路径运行时

developerAI

Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.

Installation

dsh plugin --profile web add github:58catmiao/dsh-sciwork

verified

Install method: GitHub · sandbox install ok, web smoke failed (L5)

Verification & Compatibility

Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.

External credentials (plugin-level): none detected

Declared DSH compatibilityfrom package.json · peerDependencies

author declared no dsh version requirement

○ The author declares no dsh version requirement — install is not blocked by version.

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)

At-a-glance → evidence in the cards below

plugin ＼ dsh	dsh 0.2.1-rc.2	dsh 0.2.1-alpha.4	dsh 0.2.1-alpha.2
v0.2.2	·	·	·

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed

v0.2.2github2026-10-21

https://github.com/58catmiao/dsh-sciwork

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).

Author badges

Embed the official badges in your README to showcase security & install-test status:

Security Report

Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.

dsh-sciworkAutomated review · daily

Static low, dynamic medium — stricter wins → overall medium.

static low→dynamic medium→overall medium

0 critical·0 high

mediumoverall · medium

1static scan · vet primaryvet AST static analysis (npm artifact or git source)

Version binding

plugin versionv0.2.2dsh manifest

scanned versionv0.2.2git2026-10-21

current versionv0.2.2same version

vet verdictclean · git

Vet is an AST static scan (npm artifact or git source).

show static findings (2)

warningnetIp · networklibrary/scripts/cdp-text.mjs:74
const r = await fetch(`http://127.0.0.1:${port}/json/list`);
warningspawnShell · shellscripts/install.mjs:352
? spawnSync(pyCmd, [researchPy, 'init'], { encoding: 'utf8', shell: true })

2dynamic auditmodel reads redacted source context · never executes plugin code

highest grademedium

merged intooverall medium

audited at2026-10-19

findings0 critical·0 high1 medium / 1 low hidden

show 2 audit findings

mediumtableTransform joins an unvalidated `project` slug into paths, escaping the library root and overwriting .research/config.jsonlib/actions.js:457
`project` comes straight from `asString(args.project)` and is never passed through resolveInside or a slug regex (every other action does resolve its paths). path.join collapses '..', so `project:'..'` + `outName:'config'` writes the trace JSON over <root>/.research/config.json (the authoritative config that later selects the Python interpreter and Origin server path) — the trace write has no overwrite guard — while `project:'../..'` drops `<outName>.csv` into <ancestor>/tables/. Reachable from the panel RPC `research/call` action `tableTransform`; impact is corrupting/creating files outside t
lowHeadless browser helper strips automation detection and spoofs UA to get past WAF challenge pageslibrary/scripts/cdp-text.mjs:58
The script launches the user's installed Edge/Chrome headless with automation flags removed and a forged UA (with a reload loop that waits for Cloudflare/Incapsula challenges to clear), then dumps page text/HTML/links to caller-chosen paths. This is deliberate anti-bot evasion against third-party publishers, run under the agent's control and not surfaced to the user; it also opens a CDP port (default 9444) that any local process can attach to for the duration of the run. (Functional bug: `os.tmpdir()` is used without importing `os`, so it only runs when SCIWORK_SCRATCH is set.)

tableTransform writes files using an unvalidated project slug (path traversal / can clobber .research/config.json); a headless-browser helper evades anti-bot WAFs. Other path handling is whitelisted and defensive.

Rule: the dynamic audit can only raise risk, never lower it (raise-only, never an exemption); a wrong raise is withdrawn by human review and the tier falls back to the static verdict. Overall verdict = the stricter of the two layers.

Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.

Activity

Last commit 2026-10-21 · activity: Active

• Repo created: 2026-10-13

• Stars: ★ 2 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/58catmiao/dsh-sciwork

Plugin notes

What is the @58catmiao/dsh-sciwork DeepSeek Harness plugin?

@58catmiao/dsh-sciwork is a DeepSeek Harness plugin maintained by @58catmiao. It is cataloged on dsh.so as a Developer plugin, with a public GitHub source, declared install command, and automated static scan results; plugins static-flagged at warn or above also carry a model-driven dynamic security audit record.

How do I install @58catmiao/dsh-sciwork?

Run dsh plugin --profile web add github:58catmiao/dsh-sciwork#v0.2.2 in a DeepSeek Harness (dsh) environment. This exact command has been verified by a real install inside an isolated windows-acl sandbox (L4).

How does the security scan relate to a manual audit?

Both layers are automated, not a manual audit: the static scan is heuristic analysis of the repository source (it can produce false positives and miss context), and the dynamic security audit has a model read the harvested source context with secret files stripped and content redacted inline — plugin code is never executed. The dynamic audit only covers plugins static-flagged at warn or above, and its conclusion can only raise the combined verdict, never exempt it. Neither layer is a manual security audit or an endorsement; before using a plugin, review the repository and installed permissions, and combine both with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-10-21

@58catmiao/dsh-sciwork

What it doesAI

Installation

Verification & Compatibility

Author badges

Security Report

Activity

Source

Author README