dsh-image-subagent

What it doesAI

Enables text-only LLMs to handle image attachments by projecting them as text placeholders and delegating to a vision subagent.

• Projects image attachments into explicit text placeholders
• Delegates image reading to a multimodal vision subagent
• Requires vision subagent with read attachment/image tools

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

Installation

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

Compatibility

Requirements

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

Security Report

Automated static scan, not manual review.

DSH.SO VETPASSED91e62b

Security reviewAutomated review · daily

PASSED

Vet static analysis found no suspicious behavior — verdict is clean.

0 critical·0 high·0 medium·100 score

Version binding

plugin version0.1.1dsh manifest

scanned commit91e62b5147762026-08-21

latest commit91e62b514776

vet verdictclean · gitscore 100

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

`[![dsh.so security](https://www.dsh.so/badge/dsh-image-subagent.svg)](https://www.dsh.so/artifact/dsh-image-subagent/)`

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

Activity

Last commit 2026-08-14 · activity: Active

Source

GitHub: github.com/yuqingsh/dsh-image-subagent