MeiShi

v0.1.0

提供QQ阅读官网公开页面书库、会员、帮助信息整理及权益说明,不涉及账号或盗版内容。

0· 122·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill claims to provide summaries and organization of QQ 阅读 public pages and the SKILL.md content is focused on exactly that. It does not request unrelated credentials or binaries. Minor inconsistency: the registry name is 'MeiShi' while SKILL.md uses name: 'qq-reading' — this is likely cosmetic but worth noting.
Instruction Scope
SKILL.md narrowly instructs the agent to visit public site pages (homepage, store, membership, help, activities) and extract publicly visible information. It explicitly prohibits accessing private account data, piracy, or bypassing membership mechanisms. The instructions do not ask the agent to read local files, environment variables, or send data to unexpected external endpoints.
Install Mechanism
This is an instruction-only skill with no install steps and no code files, so nothing is written to disk or downloaded during install.
Credentials
The skill requires no environment variables, credentials, or config paths; this is proportionate to a read-only public-web summarization skill.
Persistence & Privilege
always is false and model invocation is enabled by default (normal). The skill does not request elevated or persistent privileges and does not modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it only describes extracting public information from book.qq.com and asks for no credentials or installs. Before installing, consider: 1) verify the publisher (source/homepage are missing in registry) if you require provenance; 2) confirm your agent/platform has an appropriate and legal web-browsing capability and follows robots.txt, rate limits, and site terms of service; 3) monitor output for accidental inclusion of non-public info (the instructions forbid it, but runtime behavior depends on the agent/tooling); and 4) if you plan to share results externally, ensure they do not include copyrighted content beyond allowed public excerpts. If provenance of the skill's author matters to you, ask for a homepage or repo before use.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bmbzkr5v5jen636825c6ryx83c17y

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments