@xhuyangx1/dsh-qq-bridge

用 QQ 私聊远程驱动 DeepSeek Harness

Plugin

Verification

L4 · Install tested

Failed

Risk

LowRisk

Health

Active

Trust

Silver

Install verification: sandbox install ok, web smoke failed (L5) · tested on dsh 0.2.1-rc.2 · last checked 10-18Install verification details →

What it does

用 QQ 私聊远程驱动 DeepSeek Harness

Installation

dsh plugin --profile web add github:xhuyangx1/dsh-qq-bridge

verified

Install method: GitHub · sandbox install ok, web smoke failed (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

Declared DSH compatibilityfrom package.json · peerDependencies

author declared no dsh version requirement

○ The author declares no dsh version requirement — install is not blocked by version.

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)

At-a-glance → evidence in the cards below

plugin ＼ dsh	dsh 0.2.1-rc.2
v0.2.0	·

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed

v0.2.0github2026-10-21

https://github.com/xhuyangx1/dsh-qq-bridge

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

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

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.

dsh-qq-bridge-5Automated review · daily

Static low, dynamic medium — stricter wins → overall medium.

static low→dynamic medium→overall medium

0 critical·0 high

mediumoverall · medium

1static scan · vet primaryvet AST static analysis (npm artifact or git source)

Version binding

plugin versionv0.2.0dsh manifest

scanned versionv0.2.0git2026-10-21

current versionv0.2.0same version

vet verdictclean · git

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

show static findings (5)

warningchildProcess · code-execlib/acp.js:49
const child = spawn(this.#bin, this.#args, {
warningchildProcess · code-execlib/index.js:595
child = spawn(bin, args, {
warningshellExec · shelllib/napcat.js:28
const out = execFileSync('netstat', ['-ano', '-p', 'TCP'], {
warningshellExec · shelllib/napcat.js:41
const out = execFileSync('tasklist', ['/FI', 'IMAGENAME eq NapCatWinBootMain.exe', '/NH'], {
warningshellExec · shelllib/napcat.js:118
execFileSync('schtasks', [

2dynamic auditmodel reads redacted source context · never executes plugin code

highest grademedium

merged intooverall medium

audited at2026-10-19

findings0 critical·0 high2 medium / 1 low hidden

show 3 audit findings

mediumFail-open access control: empty allowlists plus privateOnly:false let any QQ user drive the agentlib/index.js:37
classify() only filters when the set is non-empty (`if (allowedUsers.size > 0 && !allowedUsers.has(userId)) return { ok: false }`), so an empty allowedUsers means 'everyone', and privateOnly defaults to false at line 57. If an operator enables the plugin with a minimal config, any QQ user who can DM the bot or shares a group with it can send `/dsh <anything>` and the task runs through an agent preset that has bash/read/write, i.e. arbitrary command execution on the host, plus file send-back to that user.
mediumUnvalidated OneBot-supplied media URL and get_file path allow SSRF and arbitrary local file readlib/index.js:481
media.url comes straight from the OneBot message segment and furl comes from the get_file response; neither is restricted by scheme, host or path (redirects are followed). The bytes are written into <cwd>/inbox and the path is pushed into the model prompt for the agent to read. A malicious or compromised OneBot endpoint (endpoint is configurable, accessToken defaults to empty) can therefore make the plugin fetch internal HTTP services or read any file the DSH process can read (e.g. SSH keys, .env) and have its content summarised back into the QQ chat.
lowWindows shell mode passes raw QQ task text as an argv to cmd.exe in plain headless modelib/index.js:580
When detectHeadlessMode() falls back to 'plain' (dsh <= 0.1.5 or a failing `--help`) and the binary resolves to a .cmd/.bat on Windows, spawn runs with shell:true and the user-supplied prompt is concatenated into the command line, so cmd metacharacters (&, |, >) in a QQ message can break out of the argument. The comment at line 132 claiming '参数里只有固定的开关和 UUID，没有引号风险' does not hold on this path.

QQ→DSH bridge is RCE-by-design; real risks are fail-open access defaults, unvalidated OneBot media URLs/paths (SSRF/local file read), and Windows shell arg injection in plain mode.

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 2026-10-18 · activity: Active

• Repo created: 2026-10-18

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/xhuyangx1/dsh-qq-bridge

Plugin notes

What is the @xhuyangx1/dsh-qq-bridge DeepSeek Harness plugin?

@xhuyangx1/dsh-qq-bridge is a DeepSeek Harness plugin maintained by @xhuyangx1. It is cataloged on dsh.so as a Developer plugin, with a public GitHub source, declared install command, and automated static scan results; plugins static-flagged at warn or above also carry a model-driven dynamic security audit record.

How do I install @xhuyangx1/dsh-qq-bridge?

Run dsh plugin --profile web add github:xhuyangx1/dsh-qq-bridge#v0.2.0 in a DeepSeek Harness (dsh) environment. This exact command has been verified by a real install inside an isolated windows-acl sandbox (L4).

How does the security scan relate to a manual audit?

Both layers are automated, not a manual audit: the static scan is heuristic analysis of the repository source (it can produce false positives and miss context), and the dynamic security audit has a model read the harvested source context with secret files stripped and content redacted inline — plugin code is never executed. The dynamic audit only covers plugins static-flagged at warn or above, and its conclusion can only raise the combined verdict, never exempt it. Neither layer is a manual security audit or an endorsement; before using a plugin, review the repository and installed permissions, and combine both 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 2026-10-18

@xhuyangx1/dsh-qq-bridge

What it does

Installation

Verification & Compatibility

Author badges

Security Report

Activity

Source

Author README