read_aloud_injection_guard
CommunityEnsure safe, verbatim AI injections with parity.
AuthorIdanDavidAviv
Version1.0.0
Installs0
System Documentation
What problem does it solve?
The Read Aloud Injection Guard enforces high-integrity content injections by ensuring parity between what the AI speaks and what it displays, preventing prompt hijacking and unsafe outputs in the Read Aloud extension.
Core Features & Use Cases
- Enforces verbatim parity rules so audio and text remain in lockstep.
- Documents and solidifies a deterministic workflow for surface content injections via say_this_loud.
- Applies in scenarios where the agent must surface SITREPs or plans without leaking internal prompts, maintaining safety and auditable traces.
Quick Start
Enable the Read Aloud Injection Guard by following its protocol rules and only inject content with say_this_loud after verifying verbatim parity and meaningful prose.
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: read_aloud_injection_guard Download link: https://github.com/IdanDavidAviv/virgo/archive/main.zip#read-aloud-injection-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.