god-git-workflow
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to analyze external repository data such as commit messages, PR descriptions, and file content. This creates a surface for indirect prompt injection if malicious instructions are embedded in a project's history.
- Ingestion points: Commit messages, log outputs, and PR descriptions accessed via Git commands.
- Boundary markers: No explicit delimiters are used to wrap ingested content to prevent the agent from following instructions found within the data.
- Capability inventory: The agent has access to shell execution for Git operations and script creation.
- Sanitization: No specific sanitization techniques for ingested text are described.
- [COMMAND_EXECUTION]: The skill provides extensive examples of shell commands for managing Git internals, workflows, and monorepo tools. These commands are standard for the developer persona and are intended for local execution within a project's context.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known developer tools and GitHub Actions. All identified resources (e.g., Turborepo, Nx, semantic-release, and official GitHub Actions) originate from trusted organizations or established package registries.
Audit Metadata