Sentiment Analysis
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill shows no malware-like behavior, but it advertises real stock social-media sentiment and bot detection while the included code returns random mock results.
Review this skill before relying on it for investment-related work. The included implementation appears to be a mock that produces random sentiment values, not a real social-media sentiment or bot-detection system. If you still test it, use an isolated Python environment and avoid making financial decisions based on its output.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A user or agent could treat arbitrary random sentiment scores as real market/social-media analysis, which is especially risky for stock-related decisions.
The source describes social-media crawling and NLP sentiment scoring, but the implemented function generates random mock sentiment values instead of analyzing real comments.
"股吧/雪球评论爬取" ... "# 简化版：返回模拟数据" ... "sentiment_score = np.random.uniform(40, 70)"
Clearly label this as a demo/mock skill, remove unsupported bot-detection and real-analysis claims, or implement the real data collection and NLP logic with transparent limitations before users rely on it.
Installing unpinned packages can expose users to dependency changes or supply-chain issues, although these packages are plausible for the stated analytics purpose.
The skill asks for manual installation of multiple public Python packages without pinned versions or a lockfile.
pip install akshare pandas numpy jieba snownlp
Install in an isolated Python environment and prefer pinned dependency versions or a reviewed lockfile from the skill author.