Cn Web Search Custom
v1.0.0中文网页搜索 - 聚合 17 个免费搜索引擎，无需 API Key，纯网页抓取，支持公众号/财经/技术/学术/知识搜索。
⭐ 0· 0·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
medium confidencePurpose & Capability
The declared purpose (aggregate 17 free search engines via webpage scraping) matches the runtime instructions (explicit URLs and web_fetch examples). No unrelated credentials, binaries, or install steps are requested. However, there are metadata inconsistencies: registry slug is 'cn-web-search-custom' while package.json/_meta.json use 'cn-web-search', versions differ (registry 1.0.0 vs SKILL.md 2.3.0 vs package.json 0.9.0), and ownerId in _meta.json differs from top-level owner ID; these suggest sloppy packaging or copy-paste rather than a functional mismatch, but they lower confidence and merit verification.
Instruction Scope
SKILL.md only instructs the agent to call web_fetch on public search URLs and gives engine-selection guidance. It does not instruct reading local files, environment variables, or sending data to third-party endpoints other than the listed search engines. The primary runtime action is network requests to public websites, which is consistent with the stated purpose.
Install Mechanism
No install spec or code files are required; this is an instruction-only skill. That minimizes disk-write and code-execution risk. The README/package metadata reference a GitHub repo and a 'clawhub install' example, but no installer is bundled with the skill package here.
Credentials
The skill requests no environment variables, no credentials, and no config paths. Examples use web_fetch only. There is no disproportionate access requested.
Persistence & Privilege
Flags show always:false and default agent invocation is allowed (normal). The skill does not request persistent/privileged settings or change other skills' configurations. Note: as with any web-fetching skill, autonomous invocation allows the agent to make outbound HTTP requests at runtime.
Assessment
This skill appears to be what it says: a set of instructions to fetch public search result pages. Before installing: 1) Verify the author/repository (SKILL.md references github.com/joansongjr) — metadata mismatches suggest the package may have been copied or repackaged. 2) Be aware the skill causes the agent to make network requests to many third-party sites (public search engines); consider privacy, scraping policies, rate limits, and legal/terms-of-service for those sites. 3) Test in a sandbox or with limited invocation first to observe network behavior. 4) If you require provenance, ask the publisher to fix the metadata (slug, version, ownerId) or provide the canonical GitHub repo/release used to produce this package. 5) No credentials are required, but if you plan to combine this with other skills that have secrets, avoid letting the aggregator post sensitive data into fetched queries.Like a lobster shell, security has layers — review code before you run it.
latestvk97fyzdc06wj1pwm5d9gym8329851v26
License
MIT-0
Free to use, modify, and redistribute. No attribution required.