Skillv1.0.0

ClawScan security

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

BenignFeb 11, 2026, 9:40 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only copy-critique template for WeChat Moments and its requirements and instructions are coherent with that stated purpose.
Guidance: This skill is instruction-only and poses low technical risk, but consider non-technical issues before use: outputs are persuasive copy that could be used for spam, targeted persuasion, or content that violates platform or local rules — review generated posts for legal/compliance and privacy concerns before publishing. Because the skill has no external dependencies or credential access, the main risk is misuse of the persuasive techniques it produces; monitor and moderate content accordingly.

Purpose & Capability: okName and description match the SKILL.md content: the file contains a step-by-step framework for evaluating and rewriting WeChat Moments posts. The skill declares no binaries, env vars, or installs — which is appropriate for a purely instructional copy-critique skill.
Instruction Scope: okRuntime instructions are limited to evaluating copy and producing scored feedback and rewrite suggestions. They do not instruct the agent to read files, access system state, call external endpoints, or exfiltrate credentials. No vague 'gather whatever context you need' directives are present.
Install Mechanism: okThere is no install spec and no code files, so nothing will be downloaded or written to disk. This is the lowest-risk installation profile.
Credentials: okThe skill requests no environment variables, credentials, or config paths. That is proportionate for a content-analysis/rewrite template.
Persistence & Privilege: okThe skill is not forced always-on and does not request special privileges or modify other skills. It can be invoked by the user or autonomously per platform defaults, which is typical for skills of this type.