Install verification: sandbox install ok, web smoke failed (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →
What it doesAI
DeepSeek Harness plugin that runs local AI models through Ollama's native /api/chat streaming API.
- Uses Ollama native /api/chat NDJSON streaming, no OpenAI bridge
- Browse, pull, inspect and remove local Ollama models
- Tune Temperature, Top K/P, Mirostat, Seed, thinking mode via GUI
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:orzgithub/dsh-ollama#0.1.2Install 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
○ The author declares no dsh version requirement — install is not blocked by version.
| plugin \ dsh | dsh 0.2.1-rc.2 current | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 |
|---|---|---|---|
| 0.1.2 | ✗ | ✗ | ✗ |
0.1.2github3 failed2026-10-19
https://github.com/orzgithub/dsh-ollama
✗dsh 0.2.1-rc.2current2026-10-19L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: github · https://github.com/orzgithub/dsh-ollama#0.1.2
ID: dsh-ollama@0.1.2@dsh0.2.1-rc.2 · profile: l4-sandbox
Issued: 2026-10-19 · expires: 2026-10-26
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-alpha.42026-10-16L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: github · https://github.com/orzgithub/dsh-ollama#0.1.2
ID: dsh-ollama@0.1.2@dsh0.2.1-alpha.4 · profile: l4-sandbox
Issued: 2026-10-16 · expires: 2026-10-23
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-alpha.22026-10-14L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: github · https://github.com/orzgithub/dsh-ollama#0.1.2
ID: dsh-ollama@0.1.2@dsh0.2.1-alpha.2 · profile: l4-sandbox
Issued: 2026-10-14 · expires: 2026-10-21
View checks & evidence
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:
`[](https://www.dsh.so/artifact/dsh-ollama/)`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.
Static low, dynamic low — stricter wins → overall low.
v0.1.2dsh manifest0.1.2git2026-10-210.1.2same versionclean · gitVet is an AST static scan (npm artifact or git source).
show static findings (5)
- warningnetIp · network
client.js:18"endpoint.hint": "Ollama 服务器地址,例如 http://127.0.0.1:11434", - warningnetIp · network
client.js:71"endpoint.hint": "Ollama server address, e.g. http://127.0.0.1:11434", - warningnetIp · network
client.js:201const DEFAULT_BASE_URL = "http://127.0.0.1:11434"; - warningnetIp · network
lib/config.js:33baseURL: z.string().default('http://127.0.0.1:11434').volatile(), - warningnetIp · network
lib/config.js:144baseURL: (config.baseURL ?? 'http://127.0.0.1:11434').replace(/\/+$/, ''),
show 1 audit findings
- lowConfigurable baseURL is used without scheme/host validation; full chat content and base64 images are POSTed there
lib/config.js:144The adapter POSTs the entire conversation (including images encoded via readImage) to whatever baseURL the settings hold. If the setting is changed by user error, an imported/edited profile or co-installed tooling, chat content is sent to an arbitrary HTTP endpoint and the server process will connect to internal hosts. The default is loopback and the value is only writable through the plugin's own settings UI, so no attacker-controlled path is demonstrated.
Ollama LLM provider plugin: all network I/O targets the user-configured Ollama base URL, UI rendering is escaped, params are allow-listed; no shell, eval, secret or prompt-injection risk 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 2026-09-30 · activity: Active
• Repo created: 2026-09-23
• Stars: ★ 0 · Forks: 0
• Health: Active — committed within last 30 days
Source
GitHub: github.com/orzgithub/dsh-ollama
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
