Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (KOL合作管理) match the SKILL.md content: the file provides goals, SOP steps, KPI guidance, risk/compliance notes, and reusable checklists — nothing in the skill requests unrelated capabilities.
Instruction Scope
SKILL.md stays high-level and confined to processes (scope, SOP, pilot, dashboard building, compliance). It briefly mentions '数据接入与看板搭建' (data ingestion and dashboarding) but provides no instructions to access files, env vars, or external endpoints; if an agent were extended to implement dashboards, additional privileged actions would be required but are not present here.
Install Mechanism
No install spec and no code files are present (instruction-only), so nothing will be written to disk or downloaded during install.
Credentials
No required environment variables, credentials, or config paths are declared; the skill does not request access to unrelated secrets or systems.
Persistence & Privilege
always is false and normal model invocation is allowed; the skill does not request permanent presence or system-level configuration changes.
Assessment
This skill is a non-executable SOP/checklist and appears safe to install. Consider: (1) it is high-level — if you want it to actually build dashboards or integrate with data sources you'll need to grant additional credentials later, so only provide those when you trust the implementation; (2) never paste sensitive credentials into prompts; (3) validate any templates or scripts you copy from results before running them in your environment; and (4) review compliance notes to ensure they match your local/legal requirements.Like a lobster shell, security has layers — review code before you run it.
latestvk973wv5acn73vnjchngf7jr1z583eyk9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.