Skills/npm/dsh-baton-mcp

dsh-baton-mcp@0.6.11

CAUTION· startup only

Publisher claims: "Pass the baton from Claude Code, Codex or any MCP client to a local DeepSeek Harness: an MCP server that hands off tasks, continues a specific session, shows the run live in Harness and hands the result back when it is done." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher jialaoliu · publishing for 23 daysInstalls 7,985Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y dsh-baton-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-11 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · cancel <run_id> | --session <id> stop the session's turn, sub-agents and jobs queued <run_id> edit <message...> | remove | steer change a message still waiting in Harness's queue answer <run_id> '<answers JSON>' answer the questions a run is waiting on runs [--session <id>] [--limit <n>] list recent runs
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:286 · Collapsed <details> block carrying instructions<summary>Environment variables</summary> | Variable | Default | Meaning | |---|---|---| | `DSH_BATON_BACKEND` | `auto` | `auto`, `host` or `headless` | | `DSH_BFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:304 · Collapsed <details> block carrying instructions<summary>Headless fallback details</summary> When the plugin is unreachable, the MCP server falls back to Harness's `dsh headless` command. It can only continueFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:160 · Collapsed <details> block carrying instructions<summary>What was tested, and how</summary> - **The only difference** in the hand-over runs is one line added at the end of the request: 交给 DeepSeek Harness 去做。Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.zh-CN.md:286 · Collapsed <details> block carrying instructions<summary>环境变量</summary> | 变量 | 默认值 | 作用 | |---|---|---| | `DSH_BATON_BACKEND` | `auto` | `auto`、`host` 或 `headless` | | `DSH_BATON_HOME` | `~/.dsh-baton` | 套接字和Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagesrc/register.mjs:557 · npx invocation of non-well-known package — may execute untrusted code// Whether an entry can start a server. A bare command (`npx -y dsh-baton-mcp`, as MCPFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/register.mjs:174 · npx invocation of non-well-known package — may execute untrusted code// (a launcher such as npx may sit between), or null when there is none.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/register.mjs:240 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// The command, args and env of [mcp_servers.dsh-baton] (and its .env table), as setupFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.zh-CN.md:304 · Collapsed <details> block carrying instructions<summary>备用 headless 说明</summary> 插件不可用时，MCP 服务器会自动改用 Harness 自带的 `dsh headless` 命令。它只能续接自己新建的对话，不能续接桌面版里建的对话（headless 不加载 `standard` 等智能体预设）；新建的对话也不会出现在桌面版侧边栏。Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagesrc/core.mjs:182 · npx invocation of non-well-known package — may execute untrusted code: `Update the server: \`npx -y dsh-baton-mcp@${plugin} setup\`.`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagehost/lib/client.js:36 · npx invocation of non-well-known package — may execute untrusted codeconst SETUP = 'npx -y dsh-baton-mcp setup'Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/register.mjs:235 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (env.length) out += `\n\n[mcp_servers.${NAME}.env]\n${env.map(([k, v]) => `${k} = ${tomlString(v)}`).join('\n')}`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandhost/lib/index.js:63 · File permission modification command — agent changes file ownership/permissions// A named pipe has no file to own, chmod or clean up; it disappears with itsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/bin.mjs:3 · npx invocation of non-well-known package — may execute untrusted code// start), with a command it is the CLI, so `npx dsh-baton-mcp setup` works.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈93 tok
1 file · 25 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for dsh-baton-mcp@0.6.11 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jialaoliu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jialaoliuPropose a patch to the maintainer