Back to skill
Skillv1.0.2

ClawScan security

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

Scanner verdict

BenignMar 4, 2026, 1:57 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code and instructions consistently implement logging into qinglite.cn and publishing content there; nothing requests unrelated credentials or performs unexpected network exfiltration.
Guidance
This skill will send the mobile number and verification code you provide to qinglite.cn and will POST content (including any media parameter you pass) to qinglite.cn. It does not request system credentials or read local files, but note: the code prints tokens to stdout (which could be captured in logs) and, despite SKILL.md wording, the implementation does not actually upload local files — it sends the media field as a string. Only install/use if you trust qinglite.cn and are comfortable giving it the phone/code or token. Avoid pasting tokens into other contexts and review whether you need real file uploads (the skill won't read local files to perform uploads). If you want higher assurance, request the maintainer to fix the prefix inconsistency and clarify media-handling behavior.

Review Dimensions

Purpose & Capability
okThe name/description (simulate login and publish on qinglite.cn) matches the provided code and SKILL.md. The Python files perform POSTs only to qinglite.cn endpoints described in the SKILL.md. No unrelated services, binaries, or credentials are requested.
Instruction Scope
noteSKILL.md describes exactly two actions (login, publish) and the code implements them. Minor discrepancies: SKILL.md says prefix is "+86" but login.py uses "86"; SKILL.md implies media are file paths but qinglite_platform.py sends the media parameter as a string (it does not read or upload local files). These are functional inconsistencies but not evidence of malicious behavior.
Install Mechanism
okNo install spec — instruction-only plus small Python source files. Nothing is downloaded or written during install.
Credentials
okThe skill requires no environment variables, credentials, or config paths. It only accepts user-supplied parameters (mobile, code, token, content, etc.), which is proportionate to its purpose.
Persistence & Privilege
okThe skill is not always-enabled and requests no elevated/system privileges or persistent changes. It does not modify other skills or system-wide settings.