Filter user-generated content with model armor templates and sanitization rules.
npx skills add https://github.com/wuyyyyyou/cli --skill gws-modelarmor-wuyyyyyou
Please help me install this Agent Skill. Skill: gws-modelarmor Source: https://github.com/wuyyyyyou/cli/tree/main/skills/gws-modelarmor Command: npx skills add https://github.com/wuyyyyyou/cli --skill gws-modelarmor-wuyyyyyou
This Skill enables safe AI workflows by filtering and neutralizing unsafe prompts and model outputs, reducing the risk of harmful content propagation.
Use gws-modelarmor to sanitize a prompt before forwarding it to the AI.
High-intent search queries and answers about installing and using this skill.
To sanitize user prompts, you apply modular safety templates and policy configurations that filter and neutralize unsafe inputs before they reach the AI model. This prevents harmful content propagation in assisted workflows.
Content moderation for AI responses involves cleaning model outputs using sanitization rules. This ensures harmful or disallowed content is neutralized before being returned to users in AI-assisted workflows.
Model armor templates enforce content safety by applying standardized policy configurations to prompts and responses. This modular approach ensures consistent safety enforcement across diverse use cases.
Yes, you can use prompt sanitization rules within existing AI-assisted workflows. The system filters unsafe prompts before forwarding them to the AI, reducing the risk of harmful content propagation.
The best way to prevent unsafe prompts is applying template-based enforcement and sanitization rules. This standardizes prompts and responses, neutralizing unsafe inputs before they reach the AI model.
You need response sanitization to clean model outputs and prevent harmful or disallowed content from being returned to users. This ensures safe AI workflows by neutralizing unsafe generated text.
googleworkspaceSanitize AI model responses using Google Model Armor templates.
niclasmartinsson-sysSanitize model outputs using a Model Armor template.
trymiraiValidate per-layer AI model inference outputs against traces.safetensors.
davidrrowleyDetect harmful content in text and images using Azure Content Safety APIs.
