integrity-check
OfficialSecure your AI state and outputs.
Software Engineering#security#prompt injection#integrity check#ai safety#adversarial attack#state validation
AuthorRune-kit
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill safeguards your AI's persistent state and outputs from malicious tampering, ensuring the integrity of your AI's memory and decision-making processes.
Core Features & Use Cases
- Adversarial Content Detection: Scans for prompt injection, memory poisoning, and identity spoofing in
.rune/files and agent outputs. - Integrity Verification: Validates persisted state, skill outputs, and context bus data against known threat models.
- Use Case: Before committing changes, run this Skill to automatically scan all project state files for hidden instructions or unexpected modifications, preventing subtle prompt injection attacks.
Quick Start
Run an integrity scan on the .rune/ directory to check for any suspicious files.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 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: integrity-check Download link: https://github.com/Rune-kit/rune/archive/main.zip#integrity-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 223,000+ vetted skills library on demand.