ClawHub

Multi Search Engine

v2.0.1

Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.

⭐ 530· 110k·1.7k current·1.7k all-time
byg_pyAng@gpyangyoujun
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
Name/description match the delivered artifacts: SKILL.md, config.json, and reference docs all describe URL templates for 17 search engines and advanced operators. The skill does not request unrelated binaries, env vars, or APIs.
ℹ
Instruction Scope
Runtime instructions are limited to calling web_fetch with constructed search URLs (consistent with a search helper). However the documentation explicitly lists advanced operators (e.g., intext:password, cache:, inurl:login, filetype:txt) that can be used to locate sensitive content — the instructions include examples that could facilitate scraping of exposed credentials or private data if misused. The skill itself doesn't exfiltrate data, but it provides the means to formulate sensitive queries.
✓
Install Mechanism
No install spec and no code files — this is instruction-only and does not write binaries or fetch archives. Low installation risk.
✓
Credentials
No environment variables, credentials, or config paths are requested. The declared requirements align with the documented functionality (public web searches require no API keys).
✓
Persistence & Privilege
always is false and the skill does not request any persistent system-level configuration. It is user-invocable and can be autonomously invoked by the agent per platform defaults (normal for skills).
Assessment
This skill is coherent and functions as a set of search-URL templates and examples. Before installing, consider: (1) The agent will perform web fetches to third-party search engines — do not send secrets, private tokens, or internal-only URLs as keywords because those queries may be transmitted to external sites. (2) The documentation includes operators that can locate exposed credentials or cached pages; avoid using the skill to search for or harvest sensitive data. (3) The skill has no homepage and an unknown publisher ID — if provenance matters, verify the author or prefer a published source with traceable ownership. If you proceed, test with harmless queries and prefer privacy engines (DuckDuckGo, Startpage, Brave) for sensitive searches.

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

latestvk97cdqq6h3vnprk7c34fd88wys80jfsc

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments