Skills/ClawHub/hekouwang-env-doctor-skill

hekouwang-env-doctor-skill@1.3.0

CAUTION· install only

Publisher claims: "开发环境与磁盘体检:默认只读扫描(不读用户文档内容、不联网、不上报),按数据/缓存/残留三分法给出判定与官方清理建议。clean 子命令只跑各工具官方的缓存与旧版本清理命令(npm、yarn、pnpm、brew、pip、uv),逐项确认后执行;不删除版本管理器目录、不删模型权重与容器数据;被判为残留的版本管理器只在报告里给手动卸载步骤。附 scripts/run-all-doctors.sh:会调用 claude-md-doctor 与 skill-doctor,额外报告配置与技能分数,属附加能力。" Observed in sandbox: reads credential files.

Registry ClawHubPublisher huiyonghkw · publishing for 98 daysInstalls 980Last detonated 29 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts 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

What changed since 1.2.2

vet-skills diff hekouwang-env-doctor-skill 1.2.2 1.3.0

In the sandbox, this version reached for nothing 1.2.2 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-18 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: reads credential files.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /usr/bin/mktemp
0.2sprocessexec /usr/bin/cat
0.2sprocessexec /usr/bin/rm
0.2sprocessexited 1: ./scripts/clean.sh: line 102: N: unbound variable
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: ERROR: 缺 md-doctor: /tmp/ks-detonate-TJebBE/scripts/home/.claude/skills/hekouwang-claude-md-doctor-skill
0.2sprocessbundled script run in the sandbox with no arguments
0.3sfilesystemread ~/.aws · ~/.ssh
0.3sfilesystemread ~ · ~/.docker · ~/ · ~/.config outside project
0.3sprocessexec /usr/bin/uname
0.3sprocessexec /usr/bin/df
0.3sprocessexec /usr/bin/awk
0.3sprocessexec /usr/bin/tail
0.3sprocessexec /usr/bin/sort
0.3sprocessexec /usr/bin/du
0.3sprocessexec /usr/bin/head
0.3sprocessexec /usr/bin/tr
0.3sprocess3 of 3 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

No findings across 1,430 lines in 13 files.

Cost to the agent

Instructions loaded
≈881 tok
1 file · 13 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

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim huiyonghkw: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim huiyonghkwPropose a patch to the maintainer