upss-security-guard
OfficialEnforce UPSS prompts with 6-gate security.
Authorupss-standard
Version1.0.0
Installs0
System Documentation
What problem does it solve?
High-risk prompts escaping security controls are a major risk in AI systems; UPSS Security Guard provides a runtime 6-gate protection layer that intercepts prompts and enforces strict controls before any LLM call.
Core Features & Use Cases
- 6-Gate Runtime Security: blocks prompt injection, jailbreaking attempts, role confusion, and secret data leakage at runtime.
- RBAC and Audit Trails: enforces least-privilege access and logs every prompt evaluation for compliance.
- OpenClaw Integration: seamless protection with the UPSS OpenClaw plugin, applicable to agent prompts and tool inputs.
Quick Start
Load the UPSS Security Guard into your agent runtime and initialize the 6-gate checks so that every prompt is validated before LLM execution.
Dependency Matrix
Required Modules
opensslsqlite3sha256sum
Components
scripts
💻 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: upss-security-guard Download link: https://github.com/upss-standard/universal-prompt-security-standard/archive/main.zip#upss-security-guard 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.