@summersummer-liu/dsh-su avatar

@summersummer-liu/dsh-su

SketchUp 2023 bridge plugin for DeepSeek Harness: drive a live SU session (Ruby tasks, .skp save, viewport capture) through 8 agent tools.

PluginDesktopStorageFileVision / OCR
Verification
L5 · Run tested
Verified
Risk
LowRisk
Health
Active
Trust
Gold

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 doesAI

Bridge plugin that lets DSH agents drive a live SketchUp 2023 session through 8 tools: run Ruby tasks, save .skp files, and capture viewport images.

  • 8 agent tools for controlling a live SketchUp 2023 session
  • Runs Ruby tasks directly inside the running SU instance
  • Saves .skp models and captures viewport screenshots
desktopAIfileAIvisionAI

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:summersummer-liu/dsh-su#v0.1.0
verified v0.1.0

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
package manifest not collected

package manifest not collected — the declared range is unknown.

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
v0.1.0✓
Install compatibility (by plugin version, dsh versions within)
Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed
v0.1.0github✓ 1 runtime-verified2026-10-22

https://github.com/summersummer-liu/dsh-su

✓dsh 0.2.1-rc.2current2026-10-22L5 · runtime verified
Environment & artifact
  • • Node.js: v24.14.0
  • • DSH: 0.2.1-rc.2
  • • Plugin artifact: github · https://github.com/summersummer-liu/dsh-su#v0.1.0
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-su@v0.1.0@dsh0.2.1-rc.2 · profile: l4-sandbox

Issued: 2026-10-22 · expires: 2026-10-29

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 2026-10-22
DSH version declared✓ Passed
Source: registry verification · Method: DSH version declaration · Captured 2026-10-22
L4 · Install tested✓ Passed
Install executed in confined sandbox✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-22
spec github:summersummer-liu/dsh-su#v0.1.0 · channel GitHub source · outcome ran · exit 0
check took: 4.6s
Install succeeded✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-22
spec github:summersummer-liu/dsh-su#v0.1.0 · channel GitHub source · outcome ran · exit 0
check took: 4.6s
Installed artifact confirmed✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-22
spec github:summersummer-liu/dsh-su#v0.1.0 · channel GitHub source · outcome ran · exit 0
check took: 4.6s
L5 · Run tested✓ Passed

active in loader tree (150 entries)

Sandbox install passed✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-22
spec github:summersummer-liu/dsh-su#v0.1.0 · install mode reused L4 scratch
check took: 50ms
Web boot ready✓ Passed
Source: DSH runtime · Method: web boot · Captured 2026-10-22
ready line dsh web: http://127.0.0.1:62437/?token=…
HTTP endpoint served✓ Passed
Source: DSH runtime · Method: HTTP request · Captured 2026-10-22
path / · HTTP 200 · took 50ms
Plugin active in inventory✓ Passed
Source: DSH runtime · Method: plugin inventory query · Captured 2026-10-22
verdict active · entries 150
match: include:su-modeling · dsh-su · 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.

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

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-suAutomated 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)
plugin versionv0.1.1dsh manifest
scanned versionv0.1.1git2026-10-22
current versionv0.1.1same version
vet verdictclean · git

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

show static findings (3)
  • criticaleval · code-execlib/su-bridge.js:109

    async eval(code, { timeoutMs } = {}) {

  • warningchildProcess · code-execlib/sketchup-extension.js:147

    const result = spawnSync('tasklist', ['/FI', 'IMAGENAME eq SketchUp.exe', '/FO', 'CSV', '/NH'], {

  • warningchildProcess · code-execlib/sketchup-extension.js:171

    const child = spawn(executable, args, {

2model reads redacted source context · never executes plugin code
highest grademedium
merged intooverall medium
audited at2026-10-22
findings0 critical·0 high1 medium / 1 low hidden
show 2 audit findings
  • mediumUnauthenticated loopback TCP bridge accepts arbitrary Ruby code from any local processsketchup/dsh_su_bridge/server.rb:69

    The extension binds 127.0.0.1 (PORT from %LOCALAPPDATA%\dsh-su\config.json, default 47311) and dispatches 'run'/'eval'/'reload'/'open' without any token, origin or peer check. Any process or other interactive session on the same machine can connect, load arbitrary .rb files or eval arbitrary Ruby inside SketchUp, which reaches File, system/backticks and the network as the logged-on desktop user. Remote/LAN access is blocked by the loopback bind, and a local attacker normally already has code execution, so this is a privilege/session-crossing and persistence amplifier rather than a remote hole.

  • lowsu_eval forwards agent-supplied Ruby verbatim, bypassing restrictToWorkspacelib/su-bridge.js:109

    Unlike su_run (workspace-confined .rb file, mustExist, extension check) and su_save/su_capture (isWithin workspace), the su_eval path writes the code string to %LOCALAPPDATA%\dsh-su\tmp and load()s it with no path or capability restriction, so agent code can read/write outside the workspace or start processes even with restrictToWorkspace=true. This is the plugin's documented purpose ('prefer su_run for multi-step tasks'), so the residual risk is that a prompt-injected agent turns an inspection call into host-level code execution.

dsh-su ships a loopback-only SketchUp bridge that executes arbitrary Ruby with no authentication, and the su_eval tool is likewise unrestricted; no remote attack surface found.

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 2026-10-22 · activity: Active

• Repo created: 2026-10-22

• Stars: ★ 1 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/summersummer-liu/dsh-su

Was this page helpful?