dsh-loop-engine

PluginDeveloperTerminal / ShellFile

Verification

L3 · Install spec

Failed

Risk

LowRisk

Health

Active

Trust

Silver

Install verification: sandbox install failed (L4) · tested on dsh 0.2.1-rc.2 · last checked 10-21Install verification details →

What it doesAI

Switch dsh web's agent loop engine from Settings: choose built-in loop or external CLI drivers (Claude Code, Codex, Pi, Kimi Code).

Adds a "Loop engine" dropdown in Settings to choose the agent driver.
Supports built-in loop and Claude/Codex/Pi/Kimi Code CLI drivers.
Rewrites only plugin-managed block in cordis.patch.yml, preserving user config.

developerAIterminalAIfileAI

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 dsh-loop-engine@0.2.1-rc1

security scan passed · npm package v0.2.1-rc1

Install method: npm · sandbox install failed (L4)

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 · peerDependenciesdeclared in 0.2.0-rc1

supports any of: dsh 0.1.5-rc.1–0.1.6 or dsh 0.1.7-rc.1–0.1.8 or dsh 0.2.0-rc.1–0.2.1

Based on 1 requirement(s) across 11 @deepseek-ai/dsh-* packages.

raw ranges

>=0.1.5-rc.1 <0.1.6-0 || >=0.1.7-rc.1 <0.1.8-0 || >=0.2.0-rc.1 <0.2.1-0 ×11

✗ 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-loop-engine@0.2.0-rc1 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).

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)

At-a-glance → evidence in the cards below

plugin ＼ dsh	dsh 0.2.1-rc.2	dsh 0.1.7-rc.1
v1.0.0-rc11	·	·
0.2.1-rc1	·	·
0.2.0-rc1	·	·
0.1.7-rc5	·	·
0.1.7-rc4	·	·

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed

v1.0.0-rc11github2026-09-08

https://github.com/kuun993/dsh-loop-engine

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

0.2.1-rc1npm2026-10-21

dsh-loop-engine

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

0.2.0-rc1npm2026-10-18

dsh-loop-engine

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

0.1.7-rc5npm2026-09-29

dsh-loop-engine

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

0.1.7-rc4npm2026-09-26

dsh-loop-engine

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

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:

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-loop-engineAutomated review · daily

Static low; dynamic no conclusion (static stands) → overall low.

static low→dynamic no conclusion→overall low

vet findings0 critical·0 high

lowoverall · low

1static scan · vet primaryvet AST static analysis (npm artifact or git source)

Version binding

plugin versionv0.2.1-rc1dsh manifest

scanned version0.2.1-rc1npm2026-10-24

current version0.2.1-rc1same version

vet verdictclean · npm

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

2dynamic auditmodel reads redacted source context · never executes plugin code

not in the dynamic queue (the queue only covers plugins whose static tier is medium or above — medium/high/critical; since 2026-10-24 entries rated low are not audited even when dsh-only rules logged warnings) — this does not mean the dynamic audit found it safe.

Rule (2026-10-24): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); without one, the static/vet fused tier applies. 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 static/vet.

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 2026-10-18 · activity: Active

• Repo created: 2026-08-25

• Stars: ★ 8 · Forks: 3

• Health: Active — committed within last 30 days

Source

GitHub: github.com/kuun993/dsh-loop-engine

Plugin notes

What is the dsh-loop-engine DeepSeek Harness plugin?

dsh-loop-engine is a DeepSeek Harness plugin maintained by @kuun993. It is cataloged on dsh.so as a Developer plugin for Terminal / Shell tasks, with a public GitHub source, declared install command, and automated static scan results; plugins static-flagged at warn or above also carry a model-driven dynamic security audit record.

How do I install dsh-loop-engine?

Run dsh plugin --profile web add dsh-loop-engine@0.2.1-rc1 in a DeepSeek Harness (dsh) environment. The command is parsed from the plugin manifest and its install spec is verified (L3); runtime sandbox install testing may not have run yet.

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 (it can produce false positives and miss context), and the dynamic security audit has a model read the harvested source context with secret files stripped and content redacted inline — plugin code is never executed. The dynamic audit only covers plugins static-flagged at warn or above; when it reaches a conclusion that conclusion is authoritative for the combined verdict — it may raise or lower it — and the static/vet fused verdict applies only when there is none. Exemptions stay manual: the audit never writes the suppression list. Neither layer is a manual security audit or an endorsement; before using a plugin, review the repository and installed permissions, and combine both with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-10-19

Was this page helpful?