Prompt Injection Defense

Prompt Injection Defense is an AI Engineering skill for Claude Code, published by seb1n in awesome-ai-agent-skills.

174 stars32 forkson seb1n/awesome-ai-agent-skillsAdded 2026/09/07+2% in starsRepository updated 2026/08/09

agent-skillsai-agent-skillsai-agentsawesome-listclaude-codeclaude-code-skillsclaude-skillscodexcodex-skillscontext-engineeringcursorcursor-skillsgemini-cligemini-skillsgithub-copilotmcpopenai-codexskill-mdskillswindsurf

Install in seconds

Install Prompt Injection Defense

Copy Prompt Injection Defense into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/seb1n/awesome-ai-agent-skills/tree/main/agent-security/prompt-injection-defense ~/.claude/skills/prompt-injection-defense

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/seb1n/awesome-ai-agent-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: agent-security/prompt-injection-defense/SKILL.md in seb1n/awesome-ai-agent-skills
Installs to: ~/.claude/skills/prompt-injection-defense
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3475 skills

What Prompt Injection Defense does

Prompt Injection Defense threat-models and hardens AI agents, RAG systems, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use it to map trust boundaries, reduce exposed authority, add tests, and document residual risk.

Prompt Injection Defense is cataloged under AI Engineering on DirSkills. Prompt Injection Defense comes from a repository tagged agent-skills, ai-agent-skills, ai-agents, awesome-list and claude-code.

Documentation

README

Excerpt

Prompt Injection Defense

Design for compromise of model reasoning. Prompt text and classifiers can reduce attack success, but they do not create a reliable security boundary. Keep consequential authority, authorization, validation, and policy enforcement outside the model.

Inputs

Collect or infer, and label assumptions for:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Prompt Injection Defense

What else does seb1n publish alongside Prompt Injection Defense?
Prompt Injection Defense is one of 25 skills that DirSkills catalogs from seb1n/awesome-ai-agent-skills, the repository it ships in. Its siblings there include API Design, API Integration and Agent Evaluation. Each one is a separate skill with its own page in this directory, installs the same way Prompt Injection Defense does, and is maintained by seb1n in that same repository. The rest of the collection is listed on the seb1n/awesome-ai-agent-skills page.
How does Prompt Injection Defense compare to other AI Engineering skills?
Prompt Injection Defense ranks #3236 by stars among the 3475 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Prompt Injection Defense against them. Open each page to compare what they document and how they install.