Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →
What it doesAI
Provides a KV-cache-stable skill catalog with hybrid BM25/bge-m3 search and autoRoute hints for DSH agents.
- KV-cache-stable static catalog
- Hybrid BM25 and bge-m3 skill search
- autoRoute hints for skill selection
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:QWE13-ART/dsh-skill-folder#v0.3.4Install 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
Based on 1 requirement(s) across 1 @deepseek-ai/dsh-* packages. raw ranges
^0.1.0-rc.6 ×1
✗ Running dsh 0.2.1-rc.2 is outside the declared range — the official install gate rejects it (incompatible-version).
To force-install, grant an exact-version exemption: dsh plugin allow-version dsh-skill-folder@0.3.4 0.2.1-rc.2 (the exemption lives in the local profile; this site does not assume one)
Whether it actually runs is a separate question → see the measured matrix below (L1–L5).
| plugin \ dsh | dsh 0.2.1-rc.2 current | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 | dsh 0.2.0-rc.2 | dsh 0.2.0-rc.1 |
|---|---|---|---|---|---|
| v0.3.4 | ✓ | ✓ | ✓ | ✓ | ✓ |
v0.3.4github✓ 11 runtime-verified2026-10-19
https://github.com/QWE13-ART/dsh-skill-folder
✓dsh 0.2.1-rc.2current2026-10-19L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.2.1-rc.2 · profile: l4-sandbox
Issued: 2026-10-19 · expires: 2026-10-26
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.42026-10-17L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.2.1-alpha.4 · profile: l4-sandbox
Issued: 2026-10-17 · expires: 2026-10-24
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.22026-10-11L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.2.1-alpha.2 · profile: l4-sandbox
Issued: 2026-10-11 · expires: 2026-10-18
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.0-rc.22026-10-09L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.2.0-rc.2 · profile: l4-sandbox
Issued: 2026-10-09 · expires: 2026-10-16
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.0-rc.12026-09-29L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.1
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.2.0-rc.1 · profile: l4-sandbox
Issued: 2026-09-29 · expires: 2026-10-06
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.7-rc.22026-09-25L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.7-rc.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.1.7-rc.2 · profile: l4-sandbox
Issued: 2026-09-25 · expires: 2026-10-02
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.6-alpha.22026-09-20L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.1.6-alpha.2 · profile: l3-fullscan
Issued: 2026-09-20 · expires: 2026-09-27
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.6-alpha.12026-09-16L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.1
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.1.6-alpha.1 · profile: l4-sandbox
Issued: 2026-09-16 · expires: 2026-09-23
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.5-rc.22026-09-11L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.5-rc.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.1.5-rc.2 · profile: l4-sandbox
Issued: 2026-09-11 · expires: 2026-09-18
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.3-alpha.22026-09-09L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.3-alpha.2
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dsh0.1.3-alpha.2 · profile: l3-fullscan
Issued: 2026-09-09 · expires: 2026-09-16
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓prehistory2026-10-04L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: unknown
- • Plugin artifact: github · https://github.com/QWE13-ART/dsh-skill-folder#v0.3.4
ID: dsh-skill-folder@v0.3.4@dshunknown · profile: l4-sandbox
Issued: 2026-10-04 · expires: 2026-10-11
View checks & evidence
active in loader tree (150 entries)
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:
`[](https://www.dsh.so/artifact/dsh-skill-folder/)``[](https://www.dsh.so/artifact/dsh-skill-folder/)``[](https://www.dsh.so/artifact/dsh-skill-folder/)``[](https://www.dsh.so/artifact/dsh-skill-folder/)``[](https://www.dsh.so/artifact/dsh-skill-folder/)``[](https://www.dsh.so/artifact/dsh-skill-folder/)`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.
v0.3.4dsh manifestv0.3.4git2026-10-21v0.3.4same versionclean · npmVet is an AST static scan (npm artifact or git source).
show static findings (5)
- warningnetIp · network
lib/index.js:151ollamaBase: z.string().default("http://127.0.0.1:11434").description("Ollama 地址(semanticEnabled 时使用)"), - warningnetIp · network
lib/index.js:175ollamaBase: "http://127.0.0.1:11434", - warningnetIp · network
lib/semantic.js:20const OLLAMA_BASE = "http://127.0.0.1:11434"; - warningfsWrite · files
lib/semantic.js:64fs.writeFileSync(p, JSON.stringify(obj), "utf8"); - warningfsWrite · files
lib/storage.js:90fs.writeFileSync(target, JSON.stringify(data), "utf8");
show 2 audit findings
- lowskill_search POSTs the intent text to a configurable HTTP endpoint despite the 'no network egress' claim
lib/semantic.js:100Each hybrid skill_search sends the model-generated intent string (derived from the user's task) to whatever `ollamaBase` is configured. The default is loopback, and the endpoint is set by the profile owner, not by untrusted input, so there is no SSRF/attacker-controlled destination; but the file header states 'no network egress', so a non-default config would send task text off-box without that being obvious.
- lowauto-route injects an unescaped, author-controlled skill description into the last user message
lib/index.js`desc` comes from the catalog entry and is concatenated verbatim (render.js escapes descriptions for the catalog, this path does not). A skill author can place `</skill-route>` and follow-on prose/newlines into a description so it is replayed inside a user-role message with directive framing. Impact is limited: the same description already appears in the catalog and the hint only fires on a name/alias hit, so this is an escalation of framing, not a new trust boundary.
Skill-catalog folding plugin; its fetch, fs-read and message-rewrite capabilities are bounded, fail-safe, config-gated and non-exploitable.
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 2026-09-02 · activity: Stable
• Repo created: 2026-08-30
• Stars: ★ 0 · Forks: 0
• Health: Stable — committed within 90 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
