An autonomous agent that scans pushed code for vulnerabilities inside an isolated sandbox, generates a fix through a cost-tiered LLM cascade, validates it against the project's own tests, and opens a pull request — no human in the loop.
Every push is scanned inside an ephemeral, network-disabled Docker container — the target repo is never trusted with network access.
Escalates to a paid model only when a cheaper one reports low confidence, never the other way around.
A generated fix is re-run against the project's existing test suite before any branch is pushed — a failing suite blocks the PR.
Bandit, Semgrep, Gitleaks, and Trivy findings are normalized and deduplicated into a single JSON envelope.
git clone https://github.com/ArdenDiago/llm-assisted-vulnerability-detection-and-automated-remediation-in-cicd-pipelines.git
cd llm-assisted-vulnerability-detection-and-automated-remediation-in-cicd-pipelines
pip install -r requirements.txt
ollama pull deepseek-coder:6.7b
docker build -t llm-cicd-agent:latest .
pytest tests/