authority-gradient-check
CommunityValidate instruction sources; block injections.
Legal & Compliance#multi-source#delegation#safety#escalation#authority#prompt-injection#source-validation
AuthorForexgod21
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Claude validates the authority behind every instruction before executing, preventing unsafe or unauthorized actions by ensuring proper source attribution and delegation levels.
Core Features & Use Cases
- Source validation: Checks who issued the instruction and confirms they have the authority to request it.
- Authority gradient enforcement: Applies a four-level hierarchy to prevent lower-level instructions from expanding scope or overriding higher-level intents.
- Prompt injection defense: Treats environmental content as data unless explicitly elevated, flagging injection attempts for review.
- Escalation & safety guards: Requeues or escalates ambiguous or high-risk instructions to human-in-the-loop when needed.
Quick Start
Command Claude to validate a multi-source instruction before executing any action in a complex task.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: authority-gradient-check Download link: https://github.com/Forexgod21/YVYC-Claude-Skills/archive/main.zip#authority-gradient-check Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.