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.
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
Reflection layer for DeepSeek Harness that logs agent steps as evidence chains and distills reusable experience anchored on done_when.
- Logs each step as hypothesis→task→result evidence chain
- Distills reusable experience with objective done_when
- Makes agent improve cumulatively with each action
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
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
| plugin \ dsh | dsh 0.1.5-rc.2 | dsh 0.1.3-alpha.2 | dsh 0.1.3-alpha.1 | dsh 0.1.2-rc.1 | dsh 0.1.2-alpha.1 |
|---|---|---|---|---|---|
| v2.3.0 | · | · | · | · | · |
v2.3.0github2026-09-11
https://github.com/clawdwan/orbit-dsh-plugin
Ecosystem app: not installed via dsh plugin add (a desktop / web shell) — its level reads L5 · Ecosystem app.
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:
`[](https://www.dsh.so/artifact/orbit-dsh-plugin/?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.
Static critical; dynamic medium (authoritative when present) → overall medium.
v2.3.0dsh manifestv2.3.0git2026-09-12v2.3.0same versioncritical · gitVet is an AST static scan (npm artifact or git source).
show static findings (1)
- warningnetIp · network
lib/index.js:101this.#embedUrl = typeof config.embedUrl === "string" && config.embedUrl ? config.embedUrl : "http://127.0.0.1:11434";
show 2 audit findings
- mediumorbit_review apply/outdate promotes distilled experiences to active without a user confirmation gate
lib/index.jsThe agent calls its own tools, so it can invoke orbit_review(action="apply") on pending entries produced by distillation and stamp them reviewed_by:"user" although no userQuestions card is ever shown. This bypasses the plugin's own stated 'user gate' that orbit_experience_add enforces with askApproval (fail-closed). Distillation input is agent-written ring text (task/done_when/assumption), so an attacker who can steer the agent can persist arbitrary wording as an active, scope=global experience, which orbit_ring_create then re-injects into every later session's context: a cross-session indirec
- lowDev-only verify script ships a hardcoded developer home path and imports a deployed copy
verify-orbit.mjs:7Not part of the runtime path (main is lib/index.js; the bundle patch only inserts the plugin id), so no execution risk. If published, it discloses the developer's local username/path layout and, when run manually, imports and string-scans a deployed copy from the user's profile.
Largely safe reflection plugin; one real gap lets the agent self-promote distilled experiences into a globally injected playbook without user confirmation.
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 2026-08-24 · activity: Stable
• Repo created: 2026-08-18
• 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).
Frequently asked questions
What is orbit-dsh-plugin?
orbit-dsh-plugin 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 orbit-dsh-plugin?
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 2026-10-24 (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.
