dsh-guardian-approval avatar

dsh-guardian-approval

Independent model-backed automatic approval plugin for DSH (Codex Guardian-style auto-review)

PluginDeveloperCode review
Verification
L2 · Structured
Security
Critical
Health
Active
Trust
Silver

What it doesAI

Independent model-backed automatic approval plugin for DSH, providing Codex Guardian-style auto-review.

  • Model-backed automatic approval
  • Codex Guardian-style auto-review
  • Independent plugin for DSH ecosystem

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

Installation

dsh plugin --profile web add dsh-guardian-approval

Install method: npm · 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 AUDITCRITICALbd8c18
Automated review · daily
CRITICAL

Critical issues in blocking categories (hardcoded secrets, exfiltration endpoints, destructive operations, cryptomining). Treat this plugin as high risk.

1 critical·0 warning·2 info·13 files scanned
secrets ×1
plugin version0.1.1dsh manifest
scanned commitbd8c18abcf582026-08-20
latest commitbd8c18abcf58

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 New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.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

  • R2 · info [likely] — require()(客户端加载器 factory 形参注入,DSH bundle 标准写法)
  • R9 · info [heuristic] — 循环内 += 累加(字符串拼接可能 O(n²))
  • R10 · info [heuristic] — 依赖清单:28 项(@deepseek-ai/cordis, @deepseek-ai/dsh-client-runtime, @deepseek-ai/dsh-client-ui-slots, @deepseek-ai/dsh-credentials, @deepseek-ai/dsh-host-webserver, @deepseek-ai/dsh-permission-presets, @deepseek-ai/dsh-session, @deepseek-ai/dsh-settings, @deepseek-ai/dsh-tools, @deepseek-ai/dsh-user-approval, @deepseek-ai/schemastery, @types/node, @types/react, react, typescript, vitest, @deepseek-ai/cordis, @deepseek-ai/dsh-client-runtime, @deepseek-ai/dsh-client-ui-slots, @deepseek-ai/dsh-credentials, @deepseek-ai/dsh-host-webserver, @deepseek-ai/dsh-permission-presets, @deepseek-ai/dsh-session, @deepseek-ai/dsh-settings, @deepseek-ai/dsh-tools, @deepseek-ai/dsh-user-approval, @deepseek-ai/schemastery, react,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))

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

Risk: Critical1 critical · 0 warning · 2 info

• Static heuristic scan: done (13 files)

• Dependency vulnerabilities: requires deep audit (L3+)

• Permission sandboxing: requires runtime testing (L4+)

High-risk findings · 1 / 1

  • criticalEmbedded private key materialsrc/sanitize.ts:44
    .replace(/-----BEGIN [A-Z ]*PRIVATE KEY-----[\s\S]*?-----END [A-Z ]*PRIVATE KEY-----/gu, '-----BEGIN PRIVATE KEY-----' + REDACTED + '-----EN

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: ★ 1 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/Scotlight/dsh-guardian-approval

Was this page helpful?