Prompt defense is an OpenClaw skill. Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions found in email content. It belongs to the Other collection. For background, see Rebuff - LLM Prompt Injection Defense in our wiki.
Prompt defense 邮件工具，支持读取、扫描。
Prompt defense has 2.1K downloads from the OpenClaw community.
Summarization
One-command install via OpenClaw
Installing Prompt defense in OpenClaw takes just one command. Make sure you have OpenClaw set up and running before proceeding.
Run the following command in your terminal to add Prompt defense to your OpenClaw instance:
openclaw skill install email-prompt-injection-defenseConfirm the skill is properly installed and ready to use:
openclaw skill listThe skill is now available in your OpenClaw conversations. Simply describe what you want to accomplish, and OpenClaw will automatically invoke Prompt defense when relevant.
What people do with Prompt defense:
| Author | eltemblor |
| Category | Other |
| Version | 1.0.1 |
| Updated | 2026-02-26 |
| Downloads | 2,113 |
| Score | 1,144 |
| Homepage | https://clawhub.ai/eltemblor/email-prompt-injection-defense |
GitHub - PromptDefender/PromptDefender: A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks. With Prompt defense on OpenClaw, you can handle this directly from your AI assistant.
AI prompt security is the practice of protecting AI systems from unintended behavior or exploitation through prompts. It focuses on reducing risks like prompt injection, leakage, and manipulation by s With Prompt defense on OpenClaw, you can handle this directly from your AI assistant.
The AIVA Report Generator stands out as an tool designed to simplify and enhance the creation of AI-driven investigation reports. Utilizing advanced algorithms, it processes vast amounts of With Prompt defense on OpenClaw, you can handle this directly from your AI assistant.
Run "openclaw skill install email-prompt-injection-defense" in your terminal. OpenClaw must be set up first. After install, the skill is available in your conversations automatically.
Yes. Prompt defense is free and open-source. Install it from the OpenClaw skill directory at no cost. Maintained by eltemblor.
Learn more from these authoritative sources:
Add Prompt defense to your OpenClaw setup. One command. Done.
Install SkillDiscover other popular skills in the Other category.