Security audit
Security checks for vulnerabilities and agentic risk
The skill appears non-destructive, but it advertises live multi-platform hot-topic monitoring while the code only uses a small built-in topic list and a local history database.
Review this skill as a limited local demo or helper, not as a real hot-topic monitoring tool. It does not appear to steal data or install persistence beyond its local history database, but users should not rely on it for current trends unless the publisher adds real source ingestion or narrows the description.
Stating that the skill can discover hot topics, monitor multiple platforms, and recommend topics, while apparently only supporting local history queries, is a meaningful transparency failure. The context makes this moderately dangerous because the skill is intended to inform content decisions, and inaccurate claims can cause bad operational decisions even if there is no direct code execution risk.
Stating that the skill can discover hot topics, monitor multiple platforms, and recommend topics, while apparently only supporting local history queries, is a meaningful transparency failure. The context makes this moderately dangerous because the skill is intended to inform content decisions, and inaccurate claims can cause bad operational decisions even if there is no direct code execution risk.
Stating that the skill can discover hot topics, monitor multiple platforms, and recommend topics, while apparently only supporting local history queries, is a meaningful transparency failure. The context makes this moderately dangerous because the skill is intended to inform content decisions, and inaccurate claims can cause bad operational decisions even if there is no direct code execution risk.
Stating that the skill can discover hot topics, monitor multiple platforms, and recommend topics, while apparently only supporting local history queries, is a meaningful transparency failure. The context makes this moderately dangerous because the skill is intended to inform content decisions, and inaccurate claims can cause bad operational decisions even if there is no direct code execution risk.
The manifest description is written as an instruction and usage contract entirely in Chinese, and the rest of the skill documentation also assumes Chinese-language prompts and outputs. Under the policy, locale or language constraints should either be optional or clearly justified; this file does not offer opt-in or explain why Chinese is required.
The script hardcodes a Chinese demo topic and emits user-facing output only in Chinese, which enforces a specific language choice. This is a natural-language policy issue because the file does not offer any locale selection or document that the tool is intentionally region-specific.
The manifest describes discovering and tracking hot topics across platforms such as Weibo, Zhihu, and Douyin, implying external source monitoring. In this file, all candidate topics are statically embedded in TOPICS, and no platform fetching or monitoring logic exists; the code only filters and ranks a fixed local dataset.
The code initializes and reads from topic_history to mark topics as used, but there is no insert or update path that writes selected topics back to the database. As a result, the claimed automatic deduplication/usage tracking behavior is not actually implemented by this script, beyond reading preexisting records.
The script prints all user-facing output in Chinese, including the heading and status labels, with no option for the user to select another language. This is a natural-language locale constraint visible in code strings and is not justified as a region-specific tool or presented as an opt-in choice.
This code prints a success message only in Chinese (标记成功) for all users. That creates a locale/language policy issue because the skill enforces a specific language without any opt-in or fallback.
The script prints a fixed Chinese heading (智能推荐) with no option to select language or locale. This is a natural-language policy concern because it imposes a specific language on all users rather than offering a choice or documenting a justified locale restriction.
The script prints status and history headers in Chinese literals, which imposes a specific language on all users. The file does not provide any opt-in, locale selection, or justification that this skill is intended only for Chinese-speaking or region-specific use.
No suspicious patterns detected.
