🗑️ The original repository has been deleted or made private. This page is an archival snapshot from indexing time; the install command may no longer work.

@ClearLeaf13/dsh-llamacpp-connect avatar

@ClearLeaf13/dsh-llamacpp-connect

把本地 llama.cpp 管理器里的模型接入 DeepSeek Harness — bring local llama.cpp manager models into DeepSeek Harness

Ecosystem appAI ModelsNetwork
Verification
L5 · Ecosystem app
Risk
Out of scope
Health
Stable
Trust
Silver

Install verification: Ecosystem app: not installed via dsh plugin add, so the L1-L5 plugin install-verification ladder does not apply; the security scan still runs.Install verification details →

Data as of (UTC)

What it doesAI

Brings models managed by your local llama.cpp manager into DeepSeek Harness so DSH can use local LLMs.

  • Connects a local llama.cpp model manager to DeepSeek Harness
  • Lets DSH call models running locally via llama.cpp
  • Tagged as a DSH plugin for local LLM workflows
aiAI

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

GitHub repository

Ecosystem apps are not installable via dsh plugin add: desktop / web shells install or deploy through their own release channel (GitHub Releases or the project site).

The level reads L5 · Ecosystem plugin / L5 · Ecosystem app per the three-way classification (the L1-L5 ladder does not rate them); the security scan still runs.

Verification & Compatibility◼ Ecosystem app

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

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)
◼ Ecosystem app
At-a-glance → evidence in the cards below
plugin \ dshdsh 0.1.7-rc.2dsh 0.1.7-rc.1prehistory
v0.14.1···
v0.13.7✗··
Install compatibility (by plugin version, dsh versions within)
Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed
v0.14.1github2026-09-30

https://github.com/ClearLeaf13/dsh-llamacpp-connect

Ecosystem app: not installed via dsh plugin add (a desktop / web shell) — its level reads L5 · Ecosystem app.

v0.13.7github1 failed2026-09-29

https://github.com/ClearLeaf13/dsh-llamacpp-connect

✗dsh 0.1.7-rc.22026-09-27Ecosystem app · L5 · failed
Environment & artifact
  • • Node.js: v24.14.0
  • • DSH: 0.1.7-rc.2
  • • Plugin artifact: github · https://github.com/ClearLeaf13/dsh-llamacpp-connect#v0.13.7
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
Failed
Sandbox install failed
Ecosystem app · L5 · failed

ID: dsh-llamacpp-connect@v0.13.7@dsh0.1.7-rc.2 · profile: l4-sandbox

Issued: 2026-09-27 · expires: 2026-10-04

View checks & evidence
L1 · Found✓ Passed

↳ carried from earlier record dsh-llamacpp-connect@v0.14.1@dshunknown (l3-fullscan)

Defaulted from L3✓ Passed
defaulted to passed — L3 install spec passed (full-registry L3 sweep policy)
L2 · Structured✓ Passed

↳ carried from earlier record dsh-llamacpp-connect@v0.14.1@dshunknown (l3-fullscan)

Defaulted from L3✓ Passed
defaulted to passed — L3 install spec passed (full-registry L3 sweep policy)
L3 · Install spec✓ Passed

↳ carried from earlier record dsh-llamacpp-connect@v0.14.1@dshunknown (l3-fullscan)

Install command parsed✓ Passed
Source: registry verification · Method: install spec parse · Captured 2026-09-30
DSH version declared✓ Passed
Source: registry verification · Method: DSH version declaration · Captured 2026-09-30
L4 · Install tested✓ Passed
Install executed in confined sandbox✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-09-27
spec github:ClearLeaf13/dsh-llamacpp-connect#v0.13.7 · channel GitHub source · outcome ran · exit 0
check took: 3.9s
Install succeeded✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-09-27
spec github:ClearLeaf13/dsh-llamacpp-connect#v0.13.7 · channel GitHub source · outcome ran · exit 0
check took: 3.9s
Installed artifact confirmed✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-09-27
spec github:ClearLeaf13/dsh-llamacpp-connect#v0.13.7 · channel GitHub source · outcome ran · exit 0
check took: 3.9s
L5 · Run tested✕ Failed
Sandbox install passed✓ Passed
Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-09-27
spec github:ClearLeaf13/dsh-llamacpp-connect#v0.13.7 · install mode reused L4 scratch
check took: 0ms
Web boot ready✕ Failed
plugin tree failed to load
HTTP endpoint served✕ Failed

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 dsh.so badges in your README to show this plugin's automated security-scan and install-test status:

dsh.so risk badge
`[![dsh.so risk](https://cdn.dsh.so/badge/dsh-llamacpp-connect.svg)](https://www.dsh.so/artifact/dsh-llamacpp-connect/?ref=badge)`

dsh.so is an independent community project, not affiliated with or endorsed by DeepSeek AI. Badges are maintained by dsh.so; embed links carry a ?ref= attribution parameter.

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-llamacpp-connectAutomated review · daily

Static low; dynamic medium (authoritative when present) → overall medium.

static low→dynamic medium→overall medium
dynamic findings0 critical·0 high·1 medium·1 low
mediumoverall · medium
1static scan · vet primaryvet AST static analysis (npm artifact or git source)
plugin versionv0.14.1dsh manifest
scanned versionv0.14.1git2026-10-07
current versionv0.14.1same version
vet verdictclean · git

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

show static findings (5)
  • warningnetIp · networksrc/adapter.ts:76

    const res = await fetch(`http://127.0.0.1:${port}${path}`, { signal: controller.signal })

  • warningnetIp · networksrc/config-store.ts:157

    return `http://127.0.0.1:${model.port}/v1`

  • warningnetIp · networksrc/control-client.ts:84

    return `http://127.0.0.1:${this.loc.apiPort}`

  • warningshellExec · shellsrc/scanner.ts:174

    execFile(

  • warningnetIp · networksrc/scanner.ts:112

    const res = await fetch(`http://127.0.0.1:${port}/v1/models`, {

2model reads redacted source context · never executes plugin code
highest grademedium
merged intooverall medium
audited at2026-10-19
audited artifactgit 635955ecad91bc0c37dd56800986cce0cd1f4983
findings0 critical·0 high1 medium / 1 low hidden
show 2 audit findings
  • mediumUnauthenticated POST /sync route lets any origin trigger local port scanning and provider re-registrationsrc/index.ts:830

    The route performs a state-changing full sync with no token, Origin or Host check; a plain cross-origin POST from any web page the user visits (simple request, no preflight) still executes the handler, causing netstat spawn, HTTP GET probes to every listening loopback port, manager /status queries and adapter teardown/re-registration. The response is CORS-blocked, but the side effects (repeatable loopback port scan, sync-queue churn) still happen.

  • lowDeep scan of every listening loopback port is enabled by defaultsrc/index.ts:152

    By default the plugin enumerates all listening ports >=1024 via `execFile('netstat', ['-ano'])` (src/scanner.ts:174) and issues GET /v1/models to each, so unrelated local services receive HTTP requests and the plugin builds an inventory of local listeners. Requests are loopback-only and cached (20s hit / 5min miss), limiting the practical impact.

Loopback-only runtime with defensive parsing, but the unauthenticated POST /sync route lets any origin trigger local port scans and provider churn.

Rule (2026-10-28): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); the static scan tier (vet primary, dsh backstop) applies only when there is none (not queued / audit failed / withdrawn). The audit never writes the exemption list (exemptions are manual only); a wrong conclusion is withdrawn by human review and the tier falls back to the static scan tier.

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 2026-09-29 · activity: Stable

• Repo created: 2026-09-23

• Stars: ★ 0 · Forks: 0

• Health: Stable — committed within 90 days

Source

GitHub: github.com/ClearLeaf13/dsh-llamacpp-connect

Frequently asked questions

What is @ClearLeaf13/dsh-llamacpp-connect?

@ClearLeaf13/dsh-llamacpp-connect is an ecosystem app listed on dsh.so, not a DSH plugin package: it cannot be installed with dsh plugin add and ships through the project's own release channel.

Is dsh.so or this plugin page official?

dsh.so is an independent community registry and is not affiliated with, endorsed by, or sponsored by DeepSeek AI.

How do I install @ClearLeaf13/dsh-llamacpp-connect?

This is an ecosystem app, not a plugin installable via dsh plugin add: desktop / web shells install or deploy through their own release channel. The security scan still runs, but the L1-L5 plugin install ladder does not rate it.

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, so it can produce false positives and miss context. The model-driven dynamic security audit only covers plugins static-flagged at warn or above, never executes plugin code, and its conclusion is authoritative when there is one (it may raise or lower the static tier); exemptions stay manual. Neither layer is an endorsement: review the repository and the permissions it asks for before installing, together with the verification level and health signals.

How fresh is the data on this page?

The data on this page is as of 2026-10-19 (UTC) — the most recent valid timestamp among the registry refresh, install verification, security scan and dynamic audit. Build time is never used as a data date.

Was this page helpful?