CatalogueSecurity & Compliance
Application Security Audit
Traces untrusted input from the edge of the system to the place it is executed, stored, or trusted.
What it examines
- Injection into SQL, commands, templates, and similar sinks
- Deserialization of data the application did not produce
- Requests or file reads built from a user-supplied path or URL
- Input that crosses into application logic without a check at that boundary
- Weak hashing, hardcoded keys, and tokens from a non-cryptographic random source
- Debug mode, wildcard CORS, and error pages that show a stack trace
What you get back
A findings file. Each item has the evidence, how serious it is, and a fix.
Dependencies
- An AI coding agent that reads SKILL.md files, such as Claude Code, Codex or Gemini CLI
- Read access to the repository, with its history
- Python 3 with the jsonschema package, to check findings.json before fixing anything
How it works
The audit is read-only. It follows user input from where it enters (an HTTP handler, a command-line argument, a queue consumer) to the place it is executed, stored or trusted.
It runs six checks: injection paths, unsafe deserialization, server-side request forgery and path traversal, validation at trust boundaries, weak cryptography and insecure defaults.
You get findings.json and findings.md. The remediate skill reads findings.json. It applies simple fixes with tests, asks you to approve larger changes and plans the rest.
Setup
- Unzip the download. Copy the audit and remediate folders into your agent's skills folder (for Claude Code, .claude/skills/) in the repository you want to check.
- Make sure the repository is a full clone, not a stripped copy.
- Open the repository in your agent and ask it to run the a1-application-security-audit skill.
- Check the result with the validator: pip install jsonschema, then python3 schema/validate.py findings.json.
- Ask your agent to run the a1-application-security-remediate skill using findings.json. Fix some findings and leave the rest open if you like.
Run it with your agent
Copy the prompt, fill in the parts in square brackets, and paste it into your agent.
Run the a1-application-security-audit skill on this repository. Use the full git history. Mode: audit only. Do not change any code. Write findings.json and findings.md in the repository root.
Run the a1-application-security-remediate skill using findings.json. Work through the findings I choose, and leave the rest open.