Version updated for https://github.com/Zero-Harm-AI-LLC/zero-harm-ai-gha to version v1.0.7. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary The GitHub Action zero-harm-ai-gha detects AI-specific security risks in pull requests, such as prompt injection risk, secrets exposure, and unsafe LLM tool usage. It provides automated security checks to help developers prevent misuse of large language models (LLMs) by scanning code diffs before merge and emitting annotations for review. The action supports various output formats, including GitHub Actions annotations, JSON, Markdown, and SARIF.