Back to skill
Skillv1.0.0

ClawScan security

cn-word-counter · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 29, 2026, 3:09 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code and runtime instructions match its description (a small local Python Chinese text counter), request no credentials, and do not perform network or unexpected actions.
Guidance
This skill appears coherent and low-risk: it is a tiny local Python script that counts words/characters/lines and requires no credentials or network access. Before installing, consider: (1) avoid passing sensitive secrets or personally identifiable text as a command-line argument because other local users/processes can see argv; prefer piping via stdin or reading from a file if privacy is a concern, (2) review the simple script if you want different counting behavior (e.g., Chinese character vs. word logic), and (3) on multi-user systems be mindful that command-line arguments are visible to system tools. Otherwise it is safe and proportional for the stated purpose.

Review Dimensions

Purpose & Capability
okName/description advertise a local Chinese word/char/line counter; the repository contains a single small Python script that implements exactly that functionality and no unrelated requirements.
Instruction Scope
noteSKILL.md instructs the agent to invoke scripts/word_counter.py with the text as a command-line argument. That stays within scope, but passing sensitive text on the command line can expose it to other local processes via process listings; otherwise no file reads, env access, or external network calls are present.
Install Mechanism
okNo install spec and no external dependencies; the script uses only the Python standard library. This is low-risk and proportional for the stated purpose.
Credentials
okNo environment variables, credentials, or config paths are requested or used. The script only reads sys.argv and prints JSON, which aligns with the skill's purpose.
Persistence & Privilege
okalways is false and the skill does not request persistent or elevated privileges. Autonomous invocation is allowed by default but combined with the small local scope it does not increase risk here.