Skylv Team Workflow Automation
PassAudited by ClawScan on May 4, 2026.
Overview
The skill is mostly documentation for AI expert roles and external setup, with no included code or credential use, but users should review the linked install scripts before running them.
This skill appears benign as submitted because it contains only documentation and role descriptions, not executable code. If you choose to use the external GitHub setup commands, review the repository and install script first, because those files were not included in this scan and may modify your AI-tool configuration.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Running the external script could change local OpenClaw or AI-tool configuration, and ClawScan did not inspect that script here.
The package itself has no install spec or code, but the documentation directs users to download and run an external install script that was not included in the reviewed artifacts.
git clone https://github.com/jnMetaCode/agency-agents-zh.git ... ./scripts/install.sh --tool openclaw
Before running the GitHub install script, inspect the repository contents, verify the publisher, and run it only in an environment where configuration changes are acceptable.
Sensitive project details supplied to a workflow may be carried across several role prompts or generated deliverables.
The skill describes passing outputs between multiple agent roles in an orchestrated workflow. This is aligned with the purpose, but users should be aware that information shared with one role may be reused by later roles.
多智能体协作 ... agents: - role: product-manager ... - role: ux-designer ... - role: frontend-developer ... execution: mode: sequential # 或 parallel
Avoid putting secrets or confidential data into multi-agent workflows unless you understand how the orchestrator stores and passes context.