prompt-defense is an AI skill on SkillBoss. 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. Install: tell your AI agent "set up skillboss.co/skill.md". Supports: Claude Code, Cursor, Windsurf.
Skill Source
Skill workflow
Ready for agent install
Updated Catalog sync pending

prompt-defense

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.

Page mode
This page centers the real SKILL.md file first.
SKILL.md
Raw file first
Loading SKILL.md…

Start using prompt-defense now

600+ APIs, 1300+ skills — the complete toolkit for AI agents

AI Agents

Tell your agent:

set up skillboss.co/skill.md

Auto-configures prompt-defense with base URL, auth, and model access. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible agent.

Developers

Sign up and get your API key in 60 seconds. $2 free credit included.

Sign Up Free →

Pay-as-you-go · No subscription · Credits never expire

prompt-defense — AI Skill for Claude Code & Cursor