Skills/PyPI/clawtouch-mcp

clawtouch-mcp@0.5.2

VERIFIED

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 · joined 5 days agoInstalls 291Last detonated 5d ago
$claude mcp add clawtouch-mcp -- uvx clawtouch-mcp
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-29 and scored it 89/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/clawtouch-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/clawtouch-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.1sprocessscript backend runs setup only

Static findings

HIGH
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:275 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:269 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_stdio_integration.py:38 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_self_interrupt_warn.py:6 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Context shift attemptexamples/integrations/INTEGRATIONS.md:281 · Context shift attempt — trying to change operational modeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:279 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_stdio_integration.py:155 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompt injectionexamples/integrations/INTEGRATIONS.md:281 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionexamples/integrations/INTEGRATIONS.md:269 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandtests/test_server.py:135 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Prompt injectionexamples/integrations/INTEGRATIONS.md:279 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionexamples/integrations/INTEGRATIONS.md:275 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languageexamples/integrations/INTEGRATIONS.md:281 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01