Skills/ClawHub/laomeng-zhc-agent

laomeng-zhc-agent@1.0.14

VERIFIED· install only

Publisher claims: "老孟中文编程(ZHC)智能体身份技能。当需要把 ZHC 语言服务接入编辑器或智能体运行时,或需要以智能体身份驱动 ZHC 的编译、运行、诊断、Office 导出闭环,或需要按分级门禁与冻结台账维护 ZHC 生态版本时使用本技能。适用于 LSP 接入、桥后端排障、产物降级判断、生态演进合规校验场景。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher mxh678988 · publishing for 6 daysInstalls 152Last detonated 36 min ago
$clawhub install laomeng-zhc-agent
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 1.0.13

vet-skills diff laomeng-zhc-agent 1.0.13 1.0.14

In the sandbox, this version reached for nothing 1.0.13 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 85/100 (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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/zhc.py:4144 · Python subprocess execution detectedr = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/zhc.py:4273 · Process kill command — agent can terminate processes"""按进程树强制结束。超时程序可能是 cmd/cl 的子孙进程,只 kill 直接子进程会留孤儿。"""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/zhc.py:4276 · Python subprocess execution detectedsubprocess.run(["taskkill", "/F", "/T", "/PID", str(pid)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/zhc.py:4296 · Python subprocess execution detectedp = subprocess.Popen(cmd, stdin=subprocess.DEVNULL, creationflags=旗)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/zhc.py:4045 · Python subprocess execution detectedr = subprocess.run([bat], capture_output=True, text=True, encoding="mbcs",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/zhc.py:4230 · Python subprocess execution detectedr = subprocess.run(cmd, cwd=work, capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,761 tok
1 file · 19 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.