Skill Prompt Generator
PassAudited by ClawScan on May 13, 2026.
Overview
This is an instruction-only prompt-writing skill with no code, credentials, install steps, or detected suspicious behavior; users should still review generated prompts before using them in other agents.
This skill appears safe to install as an instruction-only prompt generator. Before using any generated prompt in a real agent, review it for assumptions, tool permissions, data access, persistence, and instructions that could override the intended user goal.
Findings (1)
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.
A generated prompt could strongly shape another agent’s behavior, so unclear or overbroad generated instructions may lead to unintended downstream actions.
The skill intentionally creates prompts that may control downstream agent behavior. This is the core purpose of the skill, not hidden behavior, but it can affect how other agents interpret goals and constraints.
"可以直接交给其他 Agent 或 Skill 系统使用的 Prompt。" / "A Prompt ready to be handed to other Agents or Skill systems."
Review and edit generated prompts before giving them to another agent, especially any sections that grant authority, define tools, change stopping conditions, or make assumptions about user intent.