dsh.so
EN
English中文
@MCJF28/dsh-prompt-crafter avatar

@MCJF28/dsh-prompt-crafter

One-click prompt rewriter in the DeepSeek Harness composer: three rewrite levels, follows the model you are already chatting with.

PluginKnowledgeAI Models
Verification
L5 · Run tested
Verified
Risk
Medium
Health
Active
Trust
Silver

Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →

Install verification badge dsh 0.2.1-rc.2

What it does

One-click prompt rewriter in the DeepSeek Harness composer: three rewrite levels, follows the model you are already chatting with.

Installation

dsh plugin --profile web add dsh-prompt-crafter
verified 1.2.2

Install method: GitHub · runtime verified (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 ＼ dshdsh 0.2.1-rc.2
current
1.2.2✓
Install compatibility (by plugin version, dsh versions within)
Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed
1.2.2npm✓ 1 runtime-verified2026-10-21

dsh-prompt-crafter

✓dsh 0.2.1-rc.2current2026-10-21L5 · runtime verified
Environment & artifact
  • • Node.js: v24.14.0
  • • DSH: 0.2.1-rc.2
  • • Plugin artifact: npm · dsh-prompt-crafter@1.2.2
Levels (L1–L3 plugin-level static archive · L4/L5 newest real verdicts for this combination)
L1 static
Passed
L2 static
Passed
L3 static
Passed
L4 sandbox
Passed
L5 runtime
Passed
Install + runtime smoke verified in the dsh sandbox — installs and runs
L5 · runtime verified · valid for dsh 0.2.1-rc.2

ID: dsh-prompt-crafter@1.2.2@dsh0.2.1-rc.2 · profile: l3-fullscan

Issued: 2026-10-21 · expires: 2026-10-28

View checks & evidence
L1 · Found✓ Passed
Defaulted from L3✓ Passed
defaulted to passed — L3 install spec passed (full-registry L3 sweep policy)
L2 · Structured✓ Passed
Defaulted from L3✓ Passed
defaulted to passed — L3 install spec passed (full-registry L3 sweep policy)
L3 · Install spec✓ Passed
Install command parsed✓ Passed
Source: registry verification · Method: install spec parse · Captured 2026-10-21
DSH version declared✓ Passed
Source: registry verification · Method: DSH version declaration · Captured 2026-10-21
L4 · Install tested✓ Passed
Install executed in confined sandbox✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-18
spec dsh-prompt-crafter · channel npm package · outcome ran · exit 0
check took: 2.2s
Install succeeded✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-18
spec dsh-prompt-crafter · channel npm package · outcome ran · exit 0
check took: 2.2s
Installed artifact confirmed✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-18
spec dsh-prompt-crafter · channel npm package · outcome ran · exit 0
check took: 2.2s
Resolved version recorded✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-18
spec dsh-prompt-crafter · channel npm package · outcome ran · exit 0
check took: 2.2s
L5 · Run tested✓ Passed

active in loader tree (150 entries)

Sandbox install passed✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-18
spec dsh-prompt-crafter · install mode reused L4 scratch
check took: 240ms
Web boot ready✓ Passed
Source: DSH runtime · Method: web boot · Captured 2026-10-18
ready line dsh web: http://127.0.0.1:63826/?token=…
HTTP endpoint served✓ Passed
Source: DSH runtime · Method: HTTP request · Captured 2026-10-18
path / · HTTP 200 · took 240ms
Plugin active in inventory✓ Passed
Source: DSH runtime · Method: plugin inventory query · Captured 2026-10-18
verdict active · entries 150
match: include:dsh-prompt-crafter · dsh-prompt-crafter · phase active
phases: active 122 · null 28

L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.

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:

dsh.so risk
`[![dsh.so risk](https://www.dsh.so/badge/dsh-prompt-crafter.svg)](https://www.dsh.so/artifact/dsh-prompt-crafter/)`
dsh 0.2.1-rc.2 install verified
`[![dsh.so install · dsh 0.2.1-rc.2](https://www.dsh.so/badge/install/dsh-prompt-crafter@0.2.1-rc.2.svg)](https://www.dsh.so/artifact/dsh-prompt-crafter/)`

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-prompt-crafterAutomated review · daily

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

static medium→dynamic medium→overall medium
0 critical·1 high
mediumoverall · medium
1static scan · vet primaryvet AST static analysis (npm artifact or git source)
Version binding
plugin versionv1.2.2dsh manifest
scanned versionv1.2.2git2026-10-21
current versionv1.2.2same version
vet verdictsuspicious · npm

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

show static findings (1)
  • criticalsecretSk · secretsindex.js:174

    || 'sk-KF7KZR2M9xwq1rve7j7N0KYGgbmDfrwwuxrf2CI9Bvd7olPP',

2dynamic auditmodel reads redacted source context · never executes plugin code
highest grademedium
merged intooverall medium
audited at2026-10-19
findings0 critical·0 high3 medium / 0 low hidden
show 3 audit findings
  • mediumUser prompt drafts are transmitted to a third-party host (api.hcnsec.cn) that is never named in the UIindex.js:171

    When modelMode is 'free' (the highlighted default action of the first-run 'Free channel' toast sets exactly { modelMode: 'free' }), up to MAX_INPUT_CHARS=20000 chars of whatever the user typed are POSTed to an OpenAI-compatible endpoint outside the plugin repo's control/ownership, together with the plugin's bearer token. The settings UI displays only the model name and never the destination host, so the user cannot see where the draft goes. The /free-channel/test route additionally contacts this host on every settings-page open, leaking IP/timing.

  • mediumA live API key is hardcoded in the published plugin bundle (extractable by every installer)index.js:172

    The literal (redacted here by the harvester; present verbatim in the shipped file per the source comment『凭据内置在这里，等于对所有安装者公开』) is a bearer credential for api.hcnsec.cn distributed to every installer. Anyone can extract it from package/index.js and burn the quota or incur cost on the operator's account; it cannot be rotated without breaking all existing installs. It also sits next to an env-overridable baseURL, so an env-influencing attacker can redirect the same token to another host.

  • mediumSettings and optimize HTTP routes have no auth/CSRF check and parse the JSON body regardless of Content-Typeindex.js:480

    Because the handler ignores Content-Type and there is no token/origin check, a cross-origin 'simple' request (text/plain + JSON text, no preflight) from any web page the user visits can POST to the local DSH web server and rewrite plugin settings: force modelMode='free' (routing subsequent drafts to the external host), or set style='custom' with an attacker-authored customPrompt that becomes the system prompt for the user's next optimize call. The same applies to any local process. The optimize route is likewise unauthenticated and will spend the user's LLM quota on arbitrary 20k-char input.

No code execution or backdoor; real issues are a bundled third-party API key, user drafts sent to an external host, and unauthenticated settings/optimize HTTP routes (CSRF-able).

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 2026-10-18 · activity: Active

• Repo created: 2026-10-17

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/MCJF28/dsh-prompt-crafter

Was this page helpful?