dsh.so
EN
English中文
dsh-prolong-memory avatar

dsh-prolong-memory

PRO-LONG-style programmatic memory plugin for DeepSeek Harness (DSH): appends every durable session event to a per-workspace log.txt the agent retrieves with grep/python. Built-in write probe, /prolong status command, permission-deny counter, and a reproducible compaction A/B experiment.

PluginUI & SkinsDeveloperKnowledgeStorageMemoryFile
Verification
L2 · Structured
Security
Medium
Health
Active
Trust
Silver

What it doesAI

Appends session events to a per-workspace log.txt and retrieves them with grep/python for persistent memory.

  • Appends every durable session event to log.txt
  • Retrieves history via grep or python
  • Includes write probe and /prolong status command

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

Installation

dsh plugin --profile web add github:ycr40/dsh-prolong-memory

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 AUDITMEDIUM40d808
Security reviewAutomated review · daily
MEDIUM

Critical findings in non-blocking categories (dynamic code execution, shell execution, install scripts, obfuscation). Common in CLI/terminal plugins but worth reviewing.

2 critical·1 warning·3 info·15 files scanned
code-exec ×1shell ×1
Version binding
plugin version0.1.0dsh manifest
scanned commit40d8085b08d02026-08-20
latest commit40d8085b08d0

The 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 New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.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.

Second-opinion scan (vet · parallel evaluation)
vet: clean

vet verdict: vet: clean · score 100

  • R3 · info [certain] — 只读 process 成员（能力触达面）：process.execPath
  • R3 · info [certain] — 裸 process 引用（可能为 typeof 探测）
  • R3 · info [certain] (downgraded) — 直接访问 process.exit（Node 能力逃逸通道）
  • R6 · info [heuristic] — 字符串特征：child_process 引用
  • R9 · info [heuristic] — 无出口常驻循环（含 await，可能是合法服务循环；交由 LLM 审计复核上下文）

vet is advisory and does not change dsh’s four-tier level.

Risk: Medium2 critical · 1 warning · 3 info

• Static heuristic scan: done (15 files)

• Dependency vulnerabilities: requires deep audit (L3+)

• Permission sandboxing: requires runtime testing (L4+)

High-risk findings · 3 / 3

  • criticalChild process module usage (Node.js)experiments/compaction-ab/probe-command.mjs:2
    import { spawn, execSync } from 'node:child_process'
  • criticalShell command execution (exec / execSync)experiments/compaction-ab/probe-command.mjs:14
    const kill = () => { try { execSync(`taskkill /pid ${child.pid} /T /F`, { stdio: 'ignore' }) } catch {} }
  • warningHTTP request to a raw IP addressexperiments/compaction-ab/probe-command.mjs:11
    const base = `http://127.0.0.1:${port}`

Heuristic static scan — may produce false positives. Review the source yourself before trusting.

Activity

Last commit 2026-08-20 · activity: Active

• Repo created: 2026-08-20

• Stars: ★ 2 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/ycr40/dsh-prolong-memory

Was this page helpful?