Anjuke
v0.1.0Provides structured information from Anjuke's public pages including property listings, agent rules, services, and help documentation.
⭐ 0· 120·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description and SKILL.md all describe extracting and summarizing public Anjuke pages; there are no unrelated env vars, binaries, or installs requested, so the declared capabilities match the requested footprint.
Instruction Scope
SKILL.md limits work to public pages and explicitly disallows handling private/hidden data, which is appropriate. It is somewhat high-level (it assumes the agent can 'visit' pages and produce outputs) but does not instruct reading local files, other env vars, or sending data to unexpected external endpoints. Consider confirming how the agent performs web access and where extracted outputs are stored or transmitted.
Install Mechanism
No install spec and no code files — instruction-only skill — so nothing is written to disk or installed by the skill itself.
Credentials
The skill requests no credentials, no config paths, and no environment variables, which is proportionate for a public-web-scraping/summary helper.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skill/system configs. Autonomous invocation is allowed by default but is not combined with elevated privileges here.
Assessment
This skill appears coherent and low-risk because it only describes extracting publicly available information and asks for no credentials or installs. Before enabling, confirm (1) the agent's web-browsing/network permissions — ensure it only accesses public pages you intend, (2) where extracted data will be stored or sent (do not allow automatic posting to external endpoints you don't control), and (3) you will not paste any private credentials or non-public URLs into prompts. If you need stronger limits, restrict the agent's network access or review its outputs/logs during initial use.Like a lobster shell, security has layers — review code before you run it.
latestvk97byvx22r85q254y65mezx3tn8378m2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.