dsh-security

在 DeepSeek Harness (DSH) 内等价重建 OpenAI codex-security 安全审计能力的原生插件

PluginSecurityAI ModelsCode reviewFile

Verification

L5 · Run tested

Passed

Risk

Medium

Health

Active

Trust

Silver

Install verification: runtime verified (L5) · tested on dsh 0.1.5-rc.2 · last checked 09-15Install verification details →

What it doesAI

A native DSH plugin that rebuilds OpenAI codex-security's discover, verify, report security audit workflow using only DSH models and local JSONL state.

Discover, verify and report findings, with optional patch/fix re-verification
Two-stage same-model review dedupes candidates via identity fingerprints
No embeddings, OpenAI keys, Python or Docker; state kept in local JSONL files

securityAIcode-reviewAIfileAI

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 github:id7869/dsh-security

verified

Install method: GitHub · 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

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified◐ L4 testing · install passed○ ecosystem app✗ failed

No runtime install test (L4/L5) yet.

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:

Security Report

Automated static scan, not manual review.

DSH.SO VETMEDIUM9c7ff7

Security reviewAutomated review · daily

MEDIUM

Vet verdict is suspicious: findings need human review (exfiltration endpoints, file deletion, etc.).

0 critical·1 high·0 medium

Version binding

plugin versionv0.1.0dsh manifest

scanned version0.1.0git2026-09-15

current version0.1.0same version

vet verdictsuspicious · git

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

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

Risk details

Risk	Rule	Location	Description
high	R7	index.js:12	硬编码密钥：sk- API key（OpenAI/DeepSeek 系）

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

Activity

Last commit 2026-09-15 · activity: Active

• Repo created: 2026-09-15

• Stars: ★ 2 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/id7869/dsh-security

Plugin notes

What is the dsh-security DeepSeek Harness plugin?

dsh-security is a DeepSeek Harness plugin maintained by @id7869. It is cataloged on dsh.so as a Security plugin for Code review tasks, with a public GitHub source, declared install command, and automated static security scan.

How do I install dsh-security?

Run dsh plugin --profile web add github:id7869/dsh-security in a DeepSeek Harness (dsh) environment. This exact command has been verified by a real install inside an isolated windows-acl sandbox (L4) plus web smoke testing (L5).

How does the security scan relate to a manual audit?

The scan is automated static analysis of the repository source — a scalable first line of defense that can produce false positives and miss context; it is not a manual security audit. Before using a plugin, review the repository and installed permissions, and combine the scan with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-09-15