What it doesAI
Visual workflow plugin for DeepSeek Harness: edit DAGs in fullscreen workbench, run saved workflows via command or slash, and use image-recognition workflows.
- Fullscreen workbench with node-based DAG editing
- Run workflows via workflow_run or /workflow command
- Paste image to trigger recognition workflow, then continue text chat
AI-generated from the repo README — for reference only.
Installation
dsh plugin --profile web add github:Zzzzkd/dsh-workflow-studioInstall method: GitHub · not yet tested in container (L3+)
Compatibility
| DSH Version | Status |
|---|---|
| not stated | Declared — not tested |
Requirements
- • Node.js: not stated
- • DSH: declared "not stated"
- • External credentials: none detected
Security Report
Automated static scan, not manual review.
No critical or warning findings in the automated scan. The result is valid only for the commit hash shown.
0.2.0ff20dad9a8952026-08-20ff20dad9a895The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
vet verdict: vet: clean · score 100
- R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
- R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
- R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
- R6 · info [heuristic] — 字符串特征：process 敏感成员引用
vet is advisory and does not change dsh’s four-tier level.
• Static heuristic scan: done (15 files)
• Dependency vulnerabilities: requires deep audit (L3+)
• Permission sandboxing: requires runtime testing (L4+)
Activity
Last commit 2026-08-20 · activity: Active
• Repo created: 2026-08-20
• Stars: ★ 0 · Forks: 0
• Health: Active — committed within last 30 days