A POST or DELETE endpoint with no security requirement in your OpenAPI spec tells every generated client and gateway that anyone may call it. A real key pasted into an example ends up in your public docs. This skill finds those and six other API spec risks, and tells you how to fix each one.

Your agent runs a scanner on openapi.yaml, swagger.json and similar files, in YAML or JSON, OpenAPI 3 or Swagger 2. It works out each operation's security from the global and operation settings, follows local $refs, understands camelCase names such as accessToken, and skips POSTs to login, sign-up and webhook endpoints. It returns BLOCK, REVIEW, or NOT FLAGGED, with the file, line, reason, and a safer approach.

What it checks

BLOCK (fix before shipping)

• O01: a POST, PUT, PATCH or DELETE operation with no security

• O02: a server URL using plain http://

• O03: a real-looking API key, token or secret in an example

REVIEW (check before release)

• O11: a GET operation with no security in an API that uses auth

• O12: an API key sent in the query string

• O13: the OAuth2 implicit or password flow

• O14: HTTP Basic auth

• O15: a token or password passed as a query or path parameter

What's included

• The scanner (Python 3.9+, standard library only)

• A rules guide with the reason and safer approach for each rule

• A risky and a safe example spec, and the real report the scanner produces on the risky one

Limits

It reads the spec, not your server, and does not follow $refs to other files. NOT FLAGGED is not a guarantee.

Contents

One ZIP file with 8 files: SKILL.md, the scanner in scripts/ (3 Python files), references/rules.md (every rule with its reason and safer approach), and examples/ (2 example files plus report.md, the real scanner output on the risky example).

How to use: This is an agent skill: a folder with a SKILL.md file and Python scripts that an AI coding agent such as Claude Code, Cursor, or Codex CLI can run. Unzip it into your agent's skills folder (for Claude Code: ~/.claude/skills/), then ask your agent to check your project. The scripts also run on their own with Python 3.9 or newer, with nothing to install. They read your files only: no network access, and nothing is sent anywhere.