Skillv1.0.0

ClawScan security

小红书爆款文案生成器 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 5, 2026, 4:51 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only skill that provides templates and guidelines for writing Xiaohongshu (Little Red Book) viral copy and does not request credentials, install software, or perform unrelated actions.
Guidance: This skill is instruction-only and coherent with its stated purpose. Before installing, consider: (1) review generated copy for factual accuracy and compliance with platform rules and advertising laws, (2) avoid pasting private or sensitive data into prompts, (3) verify tone/claims to avoid misleading statements, and (4) remember the agent may invoke the skill autonomously by default—check invocation settings if you want to control when it runs.

Purpose & Capability: okName and description match the SKILL.md content: the file contains templates, hooks, examples and style guidelines for Xiaohongshu copy. There are no extra requirements (binaries, env vars, or config paths) that would be unrelated to generating marketing copy.
Instruction Scope: okSKILL.md only instructs how to compose posts (hook, body, CTA, hashtags) and provides templates and examples. It does not direct the agent to read local files, environment variables, system state, or to send data to external endpoints outside normal agent operation.
Install Mechanism: okNo install specification or code files are present; this is instruction-only so nothing is written to disk or downloaded during install.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. That is proportionate for a copy-generation/template skill.
Persistence & Privilege: okalways is false and there is no indication the skill attempts to modify agent-wide config or persist credentials. Autonomous invocation is allowed by platform default but this skill does not request elevated persistence.