Hands-on AI and security experiment · November 2026

DeepSeek Security Auditor

Building and independently reviewing a Python tool for finding common security weaknesses in source code and configuration.

← Back to Jason Harvey’s portfolio

Experimental · active development

Project overview

This project began as an experiment using the free DeepSeek coding model to build a Python security scanner. The first version provided a useful starting point, but early validation exposed weaknesses in credential detection and report handling. I then used ChatGPT to take over the independent code review, make corrections, expand regression tests and document the limitations.

The aim is to explore how AI-generated code can be tested and improved through repeatable security-focused validation, rather than assuming generated code is correct.

Important distinction: This is a pattern-based static code analyser. It is not a live website penetration-testing service, a full vulnerability assessment or a certified security product.

What the scanner checks

Credential exposure

Patterns for AWS access keys, GitHub tokens, API keys and generic hardcoded secrets.

SQL injection patterns

Risky query construction using concatenation, f-strings and formatting patterns.

Web configuration

Missing security headers and insecure HTTP references.

Unsafe code and settings

Checks involving eval, exec, unsafe pickle use, debug mode and hardcoded passwords.

Reports

HTML findings with severity levels and remediation guidance, with secret masking and duplicate-finding reduction.

Test targets

Individual files and directories, including a deliberately vulnerable synthetic sample application.

Testing and improvements

The 98 passing tests confirm the expected behaviour for the included unit and synthetic validation cases only. They do not establish perfect detection, zero false positives or production readiness.

What this experiment does not prove

A future development step would be to improve credential-format coverage, audit every report output for accidental secret leakage, add CI and broaden the synthetic test corpus.

Technology and project links

Python · pytest · static analysis · regular-expression detection · HTML reporting · AI-assisted development and code review.

DeepSeek is credited for the initial implementation. ChatGPT supported the subsequent independent review, fixes, regression testing and documentation. Claude was discussed as a possible independent reviewer, but was not used to produce the recorded test results.