Skip to content
Back to search

attack-protection

Agent skill that makes AI-written code hold up against 8 common attacks.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/orenatobr--attack-protection/badge.svg)](/listings/orenatobr--attack-protection)

HTML

<a href="/listings/orenatobr--attack-protection"><img src="/api/listings/orenatobr--attack-protection/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

For Claude Code, copy the skill folders into your personal skills directory:

git clone https://github.com/orenatobr/attack-protection.git
mkdir -p ~/.claude/skills
cp -R attack-protection/skills/* ~/.claude/skills/

Start a new Claude Code session. Skills load from the `description` in each `SKILL.md`, so they trigger on their own and can also be called by name.

Other agents: each skill is a folder with a `SKILL.md` (YAML frontmatter plus Markdown). Tools that read the Agent Skills format can load `skills/` as it is. For the rest, paste the body of the `SKILL.md` into the agent's instruction file.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 45 lines
  1. # attack-protection
  2. A checklist skill for AI coding agents. It makes the agent write, or review, code that resists eight attacks: XSS, exposed API routes, exposed API keys, an open database, SQL injection, missing rate limits, prompt injection and hallucinated packages. Before finishing, the agent walks the eight checks against the code it touched and reports each one as OK, FIXED or RISK, with file and line.
  3. ## Install
  4. For Claude Code, copy the skill folders into your personal skills directory:
  5. ```bash
  6. git clone https://github.com/orenatobr/attack-protection.git
  7. mkdir -p ~/.claude/skills
  8. cp -R attack-protection/skills/* ~/.claude/skills/
  9. ```
  10. Start a new Claude Code session. Skills load from the `description` in each `SKILL.md`, so they trigger on their own and can also be called by name.
  11. Other agents: each skill is a folder with a `SKILL.md` (YAML frontmatter plus Markdown). Tools that read the Agent Skills format can load `skills/` as it is. For the rest, paste the body of the `SKILL.md` into the agent's instruction file.
  12. ## Usage
  13. Invoke `/attack-protection`, optionally with a file, diff or path to audit. It also triggers on its own when the agent writes code that handles user input, HTML, API routes, secrets, databases, LLM calls or dependencies.
  14. ## Requirements
  15. Nothing beyond an agent that loads skills.
  16. ## Related skills
  17. Pairs well with `programming-best-practices`, which points to it for secret handling in logs.
  18. ## What is in this repo
  19. | Path | Purpose |
  20. |------|---------|
  21. | `skills/attack-protection/` | The `attack-protection` skill. |
  22. | `CHANGELOG.md` | Notable changes, in Keep a Changelog format. |
  23. | `AGENTS.md` | Rules for AI agents that edit this repo. |
  24. ## Contributing
  25. `main` is protected: changes land through a pull request with one approval. See [AGENTS.md](AGENTS.md) for the conventions.
  26. ## License
  27. MIT, see [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.