Skills/ClawHub/open-x-sys

open-x-sys@0.0.2

CAUTION· install only

Publisher claims: "OpenXSys opens a system for anything: a company, a technology, a city, a project, a codebase, a decision, or the person's own work and life. It shows how the thing really works, helps decide what to do, makes it real (pages, videos, documents, working capabilities) and keeps improving it across sessions. Use to understand, explain, anticipate, decide, design, build or review a whole: "open a system for …", "what really drives …", "break … down to first principles", "what would make … fail", "should we … or …", "what is the best way for me to …", "run Musk's algorithm on …", "open a system for me", "open my system", "open the playground", "continue"; 中文如“给……开启一个系统”“把……拆到第一性原理” “给我自己开启一个系统”“打开我的系统”“打开试验场”“继续”. Also use it when a session starts and host instructions mention an OpenXSys system, or `~/.openxsys/` or a workspace `.openxsys/` exists. Once a system is open, every later message in the conversation belongs to it. Not for one-line fact lookups or routine operations unrelated to an open system." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher gengshupeng · publishing for 0 daysInstalls 121Last detonated 27 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive command against a filesystem root or device. 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
0.0sprocessbundled script run in the sandbox with no arguments
0.4sprocessexec /usr/bin/dirname
0.4sprocessexec /usr/bin/sed
0.4sprocessexec /usr/bin/awk
0.4sprocessexec /usr/bin/cut
0.4sprocess1 of 1 bundled script run with no arguments
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

HIGH
Destructive file system command detecteddeps/install.sh:241 · Destructive file system command detectedsay " $n -> rm -rf \"$DIR/$n\" (or: npx skills remove $n -g)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedeps/openxsys.lock.json:19 · npx invocation of non-well-known package — may execute untrusted code"use": "npx [email protected] add <local path> --skill <name> -g -a <agent> -y --copy",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedeps/install.sh:241 · npx invocation of non-well-known package — may execute untrusted codesay " $n -> rm -rf \"$DIR/$n\" (or: npx skills remove $n -g)"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Refusal suppressiondisplay/share-pack.md:55 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileWhen the runtime is missing, there is no clip. Deliver the page and the static card and say once what video would add. Do not apologize at length and do not repeat it every run.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedeps/install.sh:324 · npx invocation of non-well-known package — may execute untrusted codeif npx --yes "skills@$CLI_VERSION" add "$_c" --skill "$_name" -g -a "$HOST" -y --copy >/dev/null 2>&1 && [ -f "$DIR/$_name/SKILL.md" ]; thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Refusal suppressionuse.md:65 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file…em, a leverage search with no goal), say so in one line and supply the minimum. Do not refuse, and do not quietly rebuild the route into your own. - **Carry results forward.…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Destructive command against a filesystem root or devicedeps/install.sh:241 · Destructive command against a filesystem root or devicesay " $n -> rm -rf \"$DIR/$n\" (or: npx skills remove $n -g)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈9,635 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim gengshupeng: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim gengshupengPropose a patch to the maintainer