DeepSeeker avatar

DeepSeeker

DeepSeek Harness, ready on your desktop.

Ecosystem appDesktopAI ModelsMemoryFile
Verification
L5 · Ecosystem app
Risk
Medium
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

Desktop app packaging DeepSeek Harness for easy use without terminal setup.

  • Native desktop app for Apple Silicon Macs
  • DeepSeek API key setup on first run
  • Automatic local Harness startup and supervision
desktopAImemoryAIfileAI

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.

Trends

Four lines, four questions: total stars, stars gained this week, cumulative downloads, downloads this week. The GitHub pair comes from real-read sampling — a rotating daily shard, so one plugin is re-read roughly every 5–14 days, sparser than npm; the npm pair has a value on every snapshot day. The two cumulative panels are smoothed curves with no sample markers; the two weekly panels keep their raw bars and add a 4-week moving-average trend line that strips single-week noise down to the direction of travel.

GitHub stars
0★

8 samples (roughly every 7 days), 2 of them reconstructed (dashed runs); a smoothed curve through every sample — not a daily series

09-22 → 11-14 · 8 points

Weekly star gain
+0★

Bars = the delta between two samples 5–14 days apart (negative points down, faint bars contain reconstructed points); line = 4-week moving-average trend

10-01 → 11-14 · 7 points

Cumulative downloads
—

Reconstructed backwards from the current total using daily downloads (gaps are not interpolated)

Only 0 points (< 3): no chart yet

no data yet

Weekly downloads
—

Bars = the snapshot’s last-week rolling window (official npm + npmmirror combined); line = 4-week moving-average trend — the shape of weekly demand, not a user count

Only 0 points (< 3): no chart yet

no data yet

weekly board —total board —downloads ≠ unique usersstar weekly —

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 0.2.2-rc.3dsh 0.2.2-alpha.2dsh 0.2.1-rc.5dsh 0.2.1-rc.3dsh 0.2.1-alpha.2
v0.2.0·····
v0.1.0·····
Install compatibility (by plugin version, dsh versions within)
Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed
v0.2.0github2026-11-14

https://github.com/deepseeker-app/DeepSeeker

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

v0.1.0github2026-09-11

https://github.com/deepseeker-app/DeepSeeker

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:

dsh.so risk badge
`[![dsh.so risk](https://cdn.dsh.so/badge/deepseeker.svg)](https://www.dsh.so/artifact/deepseeker/?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.

deepseekerAutomated review · daily

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

static low→dynamic medium→overall medium
dynamic findings0 critical·0 high·3 medium·1 low
mediumoverall · medium
1static scan · vet primaryvet AST static analysis (npm artifact or git source)
plugin versionv0.1.0-rc.5
scanned versionv0.2.0git2026-11-17
current versionv0.2.0same version
vet verdictclean · git

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

show static findings (9)
  • criticalmanifest-bare-fs · sandboxapps/cli/config/agent-presets/minimal/agent.cordis.yml

    Mutating filesystem tool shares a bare fs-local backend

  • warningmanifest-fs-unfenced · sandboxapps/cli/config/agent-presets/code/agent.cordis.yml

    Mutating filesystem tool has no explicit fs backend in realm

  • warningmanifest-search-unfenced · sandboxapps/cli/config/agent-presets/code/agent.cordis.yml

    Search tool reads without an explicit fs mount

  • warningmanifest-shell-unfenced · sandboxapps/cli/config/agent-presets/code/agent.cordis.yml

    Shell tool without a sandbox runner or policy in realm

  • warningmanifest-fs-unfenced · sandboxapps/cli/config/agent-presets/cordis/agent.cordis.yml

    Mutating filesystem tool has no explicit fs backend in realm

  • warningmanifest-search-unfenced · sandboxapps/cli/config/agent-presets/cordis/agent.cordis.yml

    Search tool reads without an explicit fs mount

  • warningmanifest-shell-unfenced · sandboxapps/cli/config/agent-presets/cordis/agent.cordis.yml

    Shell tool without a sandbox runner or policy in realm

  • warningmanifest-shell-unfenced · sandboxapps/cli/config/agent-presets/minimal/agent.cordis.yml

    Shell tool without a sandbox runner or policy in realm

  • warningmanifest-shell-unfenced · sandboxapps/cli/config/agent-presets/minimal/agent.cordis.yml

    Shell tool without a sandbox runner or policy in realm

2model reads redacted source context · never executes plugin code
highest grademedium
merged intooverall medium
audited at2026-10-17
audited artifactgit 4a4e23d43bbac23d0392905748bbaa40c35d5989
findings0 critical·0 high3 medium / 1 low hidden
show 4 audit findings
  • mediumThird-party @linxin666 host-surface plugins (incl. SSH) mounted with no source in the audited treepackages/bundle/web-app/cordis.patch.yml:309

    The web bundle mounts a roster of packages outside the @deepseek-ai scope (@linxin666/dsh-web-ui-all, -remote-web-ui, -live-stats, -dsh-ssh, -tool-describe-image, ...). The ssh and describe-image rows are explicitly 'surface: host', i.e. they run in the unsandboxed host process; their code is not part of the harvested tree and the file states only that 'Versions are pinned in this bundle'. Any of them can reach network, files and credentials in-process, outside the sandbox that bounds agent tools.

  • mediumSandbox mode and approval policy come from the environment; one variable yields danger-full-access + never-askpackages/bundle/base/cordis.patch.yml:175

    The shipped base layer derives both fences from the same inherited variable, with no validation or confirmation. Setting DSH_PERMISSION_MODE=danger-full-access removes the filesystem sandbox and simultaneously turns the user-approval policy into 'never'. The example composition is looser still (examples/acp-agent/cordis.yml line 30): any defined DSH_SNAPSHOT, even an unrelated or empty one, selects danger-full-access, and that file's own comment notes the bin loads a project-local .env before this config. A prompt-injected agent in an untrusted working directory then runs bash/fs operations wi

  • mediumOpt-in telemetry ships unredacted session logs to a vendor OTLP endpointpackages/bundle/base/cordis.patch.yml:151

    When a deployment sets DSH_TELEMETRY_MODE (FULL/FEEDBACK_ONLY), session-log records are exported to https://harness-telemetry.deepseeksvc.com/v1/logs (overridable via DSH_TELEMETRY_OTLP_URL) together with an anonymous user id. The row's own comment states uploading 'mirrors session-log records onto OTLP/HTTP logs with no session-telemetry/record redaction rule, so exports are the raw captured copy' — i.e. prompts, tool output, file contents and anything else entering context can leave the machine unredacted. Default is DISABLED.

  • lowcordis config !!js tag evaluates JavaScript inside the loader processpackages/bundle/base/cordis.patch.yml:101

    Config values can be arbitrary JavaScript evaluated by the cordis loader with harness-scoped helpers (dshHomePath, ctx.*, process.*). Every expression shipped in this tree is a static literal reading only env/cwd, so there is no attacker-controlled input and it is not a critical eval sink; but config files and --patch overlays are a documented extension point, so anyone able to write a cordis*.yml gains code execution in the host process rather than passive data.

DSH composition bundle: no critical code issue found; residual risks are unaudited @linxin666 host-surface plugins (incl. SSH), env-driven sandbox/approval disable, and opt-in raw session-log telemetry.

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 2026-09-10 · activity: Stable

• Repo created: 2026-08-14

• Stars: ★ 0 · Forks: 0

• Health: Stable — committed within 90 days

Source

GitHub: github.com/deepseeker-app/DeepSeeker

Frequently asked questions

What is DeepSeeker?

DeepSeeker 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 DeepSeeker?

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 2026-11-17 (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?