Naruto Multi-Agent CN

Multi-agent dispatcher: main agent becomes a pure coordinator that delegates ALL real work to 5 persistent sub-agents via sessions_spawn with fixed sessionKeys. Round-robin scheduling, speak-before-spawn protocol, session reuse. Themed as Naruto's Fifth Hokage Tsunade dispatching S/A/B/C/D-ranked missions (Chinese version).

This skill is coherent for a roleplay multi-agent dispatcher and contains only prose instructions (no installs, no requested secrets). Before enabling it, consider: 1) Session persistence: the five fixed sessionKeys create long-lived sub-agents that can accumulate memory—if you care about sensitive data, limit what you send to them. 2) Transparency: the skill instructs the coordinator to 'stop talking after spawn' and perform multiple sessions_spawn calls; check how your platform exposes sub-agent outputs/logs so you can audit what happened. 3) Source and provenance: the skill has no clear homepage/source and is user-contributed; if you need stronger assurance, ask the author for provenance or test in a controlled environment. If you accept those trade-offs, the skill appears to do what it says and doesn't require extra credentials or installs.

Type: OpenClaw Skill Name: naruto-multi-agent-cn Version: 1.5.0 The skill bundle itself is designed as a multi-agent dispatcher, explicitly forbidding the main agent from performing risky actions like `exec`, file I/O, or search (SKILL.md). However, it instructs the agent to take user input and pass it directly into the `task` parameter of `sessions_spawn` for delegation to sub-agents. This creates a significant prompt injection vulnerability, as a malicious user could craft harmful instructions that would then be executed by the downstream sub-agents, making it a risky capability without clear malicious intent within this skill.