dsh.so
EN
English中文
dsh-llm-pi-ai-headers avatar

dsh-llm-pi-ai-headers

为dsh提供商添加自定义请求头

PluginAI Models
Verification
L2 · Structured
Security
Medium
Health
Active
Trust
Silver

What it doesAI

Adds per-provider custom request headers and retry policy configuration for dsh LLM providers.

  • Configure request headers per provider in settings sidebar
  • Edit retry policy: mode, max retries, error codes, backoff
  • Restores User Agent dropped by official adapter filter

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

Installation

dsh plugin --profile web add github:xsluck/dsh-llm-pi-ai-headers

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 AUDITMEDIUM1e6a11
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.

1 critical·6 warning·6 info·7 files scanned
code-exec ×1
Version binding
plugin version0.3.0dsh manifest
scanned commit1e6a117c49092026-08-20
latest commit1e6a117c4909

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 New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.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 81

  • R10 · info [heuristic] — 依赖清单：6 项（@deepseek-ai/dsh-launch-environment, @deepseek-ai/dsh-llm, @deepseek-ai/dsh-llm-pi-ai, @deepseek-ai/dsh-settings, @deepseek-ai/schemastery, @earendil-works/pi-ai，供 LLM 审计供应链；已知漏洞核对见后续 OSV 精确版本查询（网络失败静默降级））
  • R12 · info [heuristic] (downgraded) — engines.node=>=18 低于 DSH 运行要求（>=22.19），可能不兼容
  • 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

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

Risk: Medium1 critical · 6 warning · 6 info

• Static heuristic scan: done (7 files)

• Dependency vulnerabilities: requires deep audit (L3+)

• Permission sandboxing: requires runtime testing (L4+)

High-risk findings · 7 / 7

  • criticalChild process module usage (Node.js)install.mjs:22
    import { spawnSync } from 'node:child_process'
  • warningFilesystem write operationsinstall.mjs:105
    await fs.writeFile(backup, src)
  • warningFilesystem write operationsinstall.mjs:178
    await fs.writeFile(bundle, src)
  • warningFilesystem write operationsinstall.mjs:195
    await fs.writeFile(pluginDst, await fs.readFile(pluginSrc))
  • warningFilesystem write operationsuninstall.mjs:47
    await fs.writeFile(args.client, await fs.readFile(backup))
  • warningFilesystem write operationsuninstall.mjs:61
    await fs.writeFile(client, await fs.readFile(backup))
  • warningFilesystem write operationsuninstall.mjs:84
    await fs.writeFile(patchYml, yml)

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: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/xsluck/dsh-llm-pi-ai-headers

Was this page helpful?