Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
微信自动写作排版专业技能（包含公众号发布功能）
v2.0.0支持微信公众号深度内容从Markdown写作、爆款方法论指导、94种排版主题选择到图片上传、草稿创建及一键发布的全流程管理。
⭐ 1· 56·0 current·0 all-time
by龚玎焕@gongdinghuan
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description and included knowledge files are coherent with a WeChat writing + publishing skill. However the SKILL.md and code samples rely on WeChat credentials (AppID/AppSecret/Access Token) and an OpenClaw built-in tool named `wechat_publisher` — yet the skill metadata lists no required environment variables, no primary credential, and no required binaries. The omission of required credentials in metadata is a mismatch and reduces transparency.
Instruction Scope
Runtime instructions tell the agent to read local knowledge files (expected) and to perform publishing via either a platform-provided `wechat_publisher` tool or direct calls to WeChat API. The guide includes concrete network calls (api.weixin.qq.com) and Python examples that open local image files and POST them. The instructions therefore require access to local files and sensitive App credentials (implied) but do not explicitly constrain or declare those requirements in the manifest.
Install Mechanism
Instruction-only skill with no install spec and no downloaded code; nothing is written to disk by an installer. This is the lowest-risk install pattern.
Credentials
The SKILL.md and examples clearly require AppID/AppSecret and an Access Token to call WeChat APIs and to upload/publish content. The skill metadata declares no required environment variables or primary credential. Asking users to provide those secrets at runtime is reasonable for publishing functionality, but the skill should declare them explicitly so users know what will be requested and stored.
Persistence & Privilege
The skill does not request always:true and does not claim system-wide modifications. Autonomous invocation is allowed (platform default) but not combined with other high-privilege requests. No evidence the skill writes persistent config or modifies other skills.
What to consider before installing
This package appears to be a legitimate WeChat article formatting and publishing guide, but it has important transparency gaps. Before installing or enabling automatic publishing: (1) Confirm whether your OpenClaw environment actually provides the referenced `wechat_publisher` tool — if not, the skill's one-click functions won't work. (2) Expect to supply WeChat AppID and AppSecret (or equivalent credentials); the skill does not declare them in metadata — demand the author add required env var names (e.g., WECHAT_APPID, WECHAT_APPSECRET) and explain storage/rotation. (3) Never paste credentials into skill text; use environment variables or a secrets manager and enable IP whitelisting in the official WeChat backend. (4) Test publishing in a sandbox account and keep manual review in the loop (do not enable fully automatic publish) until you confirm behavior. (5) If you need greater assurance, ask the author to include explicit manifest fields for required credentials and to document any external dependencies or expected built-in tools.Like a lobster shell, security has layers — review code before you run it.
latestvk97ejt0xahf9gfy2pb82g9jka18439e7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.