Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →
What it doesAI
Bridges Codex into DSH as an architect and read-only reviewer with ChatGPT sign-in, model choice, file approval and checkpoints.
- ChatGPT sign-in to use Codex models
- Two roles: architect and read-only reviewer
- Explicit file approval and checkpoint control
Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.
Installation
dsh plugin --profile web add dsh-codex-architectInstall method: npm · runtime verified (L5)
Verification & Compatibility
Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.
External credentials (plugin-level): none detected
○ The author declares no dsh version requirement — install is not blocked by version.
| plugin \ dsh | dsh 0.2.1-rc.2 current | dsh 0.2.1-alpha.2 |
|---|---|---|
| 0.2.0 | ✓ | ✓ |
0.2.0npm✓ 2 runtime-verified2026-10-19
dsh-codex-architect
✓dsh 0.2.1-rc.2current2026-10-19L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: npm · dsh-codex-architect@0.2.0
ID: dsh-codex-bridge-4@0.2.0@dsh0.2.1-rc.2 · profile: l4-sandbox
Issued: 2026-10-19 · expires: 2026-10-26
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.22026-10-15L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: npm · dsh-codex-architect@0.2.0
ID: dsh-codex-bridge-4@0.2.0@dsh0.2.1-alpha.2 · profile: l3-fullscan
Issued: 2026-10-15 · expires: 2026-10-22
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).
Author badges
Embed the official badges in your README to showcase security & install-test status:
`[](https://www.dsh.so/artifact/dsh-codex-bridge-4/)``[](https://www.dsh.so/artifact/dsh-codex-bridge-4/)`Security Report
Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.
Static low, dynamic low — stricter wins → overall low.
v0.2.0dsh manifest0.2.0npm2026-10-210.2.0same versionclean · npmVet is an AST static scan (npm artifact or git source).
show static findings (7)
- warningchildProcess · code-exec
src/catalog.mjs:7const child = spawn(executable, ['app-server', '--stdio', '-c', 'forced_login_method="chatgpt"', '-c', 'model_provider="openai"'], { cwd, en - warningfsWrite · files
src/changes.mjs:60await fs.writeFile(temp, record.after, { flag: 'wx', mode: 0o600 }); - warningfsWrite · files
src/changes.mjs:95await fs.writeFile(temp, Buffer.from(record.before, 'base64'), { flag: 'wx' }); - warningfsWrite · files
src/codex.mjs:54await fs.writeFile(schema, JSON.stringify(schemaFor(job.kind))); - warningchildProcess · code-exec
src/process.mjs:7const child = spawn(executable, args, { cwd, env, shell: false, windowsHide: true, stdio: ['pipe', 'pipe', 'pipe'] }); - warningchildProcess · code-exec
src/process.mjs:13const killer = spawn('taskkill.exe', ['/PID', String(child.pid), '/T', '/F'], { shell: false, windowsHide: true, stdio: 'ignore' }); - warningfsWrite · files
src/store.mjs:18await fs.writeFile(temp, JSON.stringify(value, null, 2), { mode: 0o600 });
show 2 audit findings
- lowCodex-generated handoff injected into DeepSeek as a user message without prior display
src/bridge.mjsModel-influenced text (repo content can bias Codex) is delivered to the coding agent with source kind 'user' and is not shown before the agent acts (only /codex show reveals it), so it can steer DeepSeek into unintended actions.
- lowSensitive changed-file names leak into Codex context despite content filtering
src/context.mjs:35The changed git path list is placed in the prompt sent to the external Codex service without sensitive()/relativePath() filtering, so names like .env.production or id_rsa can be disclosed even though their contents are excluded.
Defensively written Codex bridge: spawns with shell:false and filtered env, read-only Codex sandbox, path/symlink checks, digest-gated writes; only two low-severity transparency/metadata issues found.
Rule: the dynamic audit can only raise risk, never lower it (raise-only, never an exemption); a wrong raise is withdrawn by human review and the tier falls back to the static verdict. Overall verdict = the stricter of the two layers.
Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.
Activity
Last commit 2026-10-14 · activity: Active
• Repo created: 2026-10-14
• Stars: ★ 0 · Forks: 0
• Health: Active — committed within last 30 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
