Skills/ClawHub/computer

computer@1.0.0

CAUTION· static only

Publisher claims: "Universal computer skill split by operating system. Comprehensive system management, hardware diagnostics, performance monitoring, and optimization across Li..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher acupai · publishing for 253 daysInstalls 1,995Last detonated 22 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command; Privileged sudo command. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Process kill commandSKILL.md:288 · Process kill command — agent can terminate processeskill -STOP PID # 暂停(SIGSTOP)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:86 · Privileged sudo command — agent may execute with elevated privilegessudo dmidecode --type memory # 内存模块详情Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:87 · Privileged sudo command — agent may execute with elevated privilegessudo lshw -C memory # 硬件层信息Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:287 · Process kill command — agent can terminate processeskill -9 PID # 强制杀死Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:591 · File permission modification command — agent changes file ownership/permissionschown root:dialout device_fileFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandSKILL.md:54 · Privileged sudo command — agent may execute with elevated privilegessudo dmidecode --type system # DMI表信息(Linux)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:153 · Privileged sudo command — agent may execute with elevated privilegessudo turbostat --all # Intel CPU功耗、温度Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:286 · Process kill command — agent can terminate processeskill -15 PID # 优雅终止Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:334 · Privileged sudo command — agent may execute with elevated privilegesecho "performance" | sudo tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governorFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:590 · File permission modification command — agent changes file ownership/permissionschmod 660 device_fileFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandSKILL.md:289 · Process kill command — agent can terminate processeskill -CONT PID # 继续(SIGCONT)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,217 tok
1 file · 2 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

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim acupai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. 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 ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim acupaiPropose a patch to the maintainer