Skip to content
appsgit

Safety Scan

Safety Scan is an agent skill (a SKILL.md file) from ruvnet/ruflo. Scan inputs for prompt injection, unsafe content, and adversarial attacks using AIDefence. It works with Claude Code and Codex and has 79,349 GitHub stars across a repository of 7 listed skills.

github.com/ruvnet/ruflo/plugins/ruflo-aidefence/skills/safety-scan (opens in a new tab)

Data as of from the GitHub API; description from the skill's SKILL.md. Report an error

View on GitHub (opens in a new tab)

Add this skill

Claude

This repository is a Claude Code plugin marketplace. In Claude Code:

/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-aidefence@ruflo

In the Claude apps, zip the safety-scan folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/ruvnet/ruflo.git
cp -r ruflo/plugins/ruflo-aidefence/skills/safety-scan .agents/skills/safety-scan   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/ruvnet/ruflo.git
cp -r ruflo/plugins/ruflo-aidefence/skills/safety-scan .cursor/skills/safety-scan   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

Scan inputs for prompt injection, unsafe content, and adversarial attacks using AIDefence. Use when processing untrusted input (user submissions, API payloads, webhook data, tool outputs) before passing it to a model or executing it. Scan content for prompt injection, jailbreak attempts, and unsafe patterns.

When it triggers

  • Use when processing untrusted input (user submissions, API payloads, webhook data, tool outputs) before passing it to a model or executing it.

More skills in ruvnet/ruflo

7 skills are listed from this repository.

Similar skills

More data & analysis skills

All Data & analysis

FAQ

Safety Scan FAQ

Still curious? Email info@appsgit.com.

How do I install the Safety Scan skill?

In Claude Code, run /plugin marketplace add ruvnet/ruflo and then /plugin install ruflo-aidefence@ruflo. For Codex or Cursor, copy the safety-scan folder into .agents/skills/ or .cursor/skills/.

Is the Safety Scan skill free?

Yes. The repository is open source under the MIT license.

Is Safety Scan maintained?

The repository's most recent commit was on Oct 26, 2026. Its latest release is v3.63.1. appsgit only lists skills from repositories with a commit in the last six months.