Skills/PyPI/clawtouch-mcp

clawtouch-mcp@0.6.0

VERIFIED· not started

Publisher claims: "MCP stdio server exposing HID mouse/keyboard tools backed by ClawTouch Pico hardware." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher tinqiao-oss · publishing for 172 daysInstalls 239Last detonated 1 h ago
$claude mcp add clawtouch-mcp -- uvx clawtouch-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified 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
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. 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 -- uvx clawtouch-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; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtests/test_stdio_integration.py:38 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_server.py:135 · Process kill command — agent can terminate processes# used to hit AttributeError on msg.get() and kill the whole stdioFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injectionexamples/integrations/INTEGRATIONS.md:279 · Prompt injection — known jailbreak technique reference · informational: not an instruction file**ChatGPT Desktop (Developer Mode):**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/integrations/INTEGRATIONS.md:275 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- ChatGPT Developer Mode — <https://platform.openai.com/docs/guides/developer-mode>Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedtests/test_stdio_integration.py:155 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionexamples/integrations/INTEGRATIONS.md:269 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileOpenAI ships MCP client support in **ChatGPT Desktop** (DeveloperFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandtests/test_self_interrupt_warn.py:6 · Process kill command — agent can terminate processescombo that would kill the agent if the MCP server shares a machine with itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:281 · Authorization escalation language · informational: not an instruction file1. Enable Developer Mode — Settings → Beta features → Developer modeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:269 · Authorization escalation language · informational: not an instruction fileOpenAI ships MCP client support in **ChatGPT Desktop** (DeveloperFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionexamples/integrations/INTEGRATIONS.md:281 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. Enable Developer Mode — Settings → Beta features → Developer modeFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:275 · Authorization escalation language · informational: not an instruction file- ChatGPT Developer Mode — <https://platform.openai.com/docs/guides/developer-mode>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Context shift attemptexamples/integrations/INTEGRATIONS.md:281 · Context shift attempt — trying to change operational mode · informational: not an instruction file1. Enable Developer Mode — Settings → Beta features → Developer modeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:279 · Authorization escalation language · informational: not an instruction file**ChatGPT Desktop (Developer Mode):**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈58 tok
1 file · 57 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 clawtouch-mcp@0.6.0 as of 41 min ago. This is the package itself, not its dependencies.