Skillv1.0.0

ClawScan security

小红书算法优化师 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 11, 2026, 3:55 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only Xiaohongshu content-optimization guide and its requested resources, instructions, and files are consistent with that purpose.
Guidance: This skill is an offline instruction-only assistant for writing Xiaohongshu posts and appears internally consistent. Before installing or using it: (1) confirm you won't paste or ask it to process sensitive/private data (it has no built-in data-exfil mechanisms, but pasted content could contain secrets); (2) follow platform rules — the included forbidden-words list is helpful but you remain responsible for legal/advertising compliance; (3) if you need integrations (posting directly to Xiaohongshu, analytics, or account automation) expect additional credentials and a new security review because this skill currently has none.

Purpose & Capability: okName/description (Xiaohongshu content optimization) align with the provided instructions and reference files (title examples, forbidden words). The skill declares no binaries, env vars, or external services, which is appropriate for a purely editorial optimization tool.
Instruction Scope: okSKILL.md contains step-by-step editorial guidance, output format, and forbidden-word lists. It does not instruct reading system files, accessing environment variables, making network calls, or transmitting data to external endpoints. Scope remains limited to transforming/producing text for Xiaohongshu posts.
Install Mechanism: okNo install spec or code present (instruction-only). Nothing is downloaded or written to disk; therefore there is no install risk.
Credentials: okThe skill requests no environment variables, credentials, or config paths. This is proportionate for an editorial assistant that only needs copy/structure suggestions.
Persistence & Privilege: okalways is false and the skill is user-invocable. It does not request persistent system presence or modify other skills/config. Autonomous invocation is allowed but not excessive for this type of skill.