dsh-vision-plugin avatar

dsh-vision-plugin

PluginVisionVision / OCR
Verification
L1 · Found
Security
Medium
Health
Active
Trust
Unrated

What it doesAI

Adds image understanding to DeepSeek Harness by using an external vision model to describe images for text-only main models.

  • Wires OpenAI-compatible external vision models
  • Gives text-only models a describe-image tool
  • Understands screenshots, photos, charts, OCR, UIs

AI-generated from the repo README — for reference only.

Installation

dsh plugin --profile web add github:woyeshishen/dsh-vision-plugin

Install method: GitHub · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO VETMEDIUMf001cd
Automated review · daily
MEDIUM

Vet verdict is suspicious: findings need human review (exfiltration endpoints, file deletion, etc.).

0 critical·1 high·0 medium·84 score
plugin version1.0.4dsh manifest
scanned commitf001cdb874b22026-08-21
latest commitf001cdb874b2
vet verdictsuspicious · npmscore 84

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

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Risk details

RiskRuleLocationDescription
high
R14
install.ps1:13
脚本下载即执行:PowerShell Invoke-Expression(脚本随包分发,安装/运行期任意代码执行面)
Heuristic static scan — may produce false positives. Review the source yourself before trusting.

Activity

Last commit 2026-08-15 · activity: Active

• Repo created: 2026-08-21

• Stars: ★ 3 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/woyeshishen/dsh-vision-plugin

Was this page helpful?