coderabbit-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages administrative repository tasks through transparent shell commands. All operations are aligned with the documented purpose of ensuring production readiness for a code review service.
- [COMMAND_EXECUTION]: Employs the GitHub CLI (
gh api) to retrieve pull request metadata and update branch protection settings. These interactions are standard for repository management and are restricted to official GitHub endpoints. - [DYNAMIC_EXECUTION]: Uses a Python script to validate the syntax of
.coderabbit.yaml. The implementation utilizesyaml.safe_load(), following security best practices to prevent arbitrary code execution during the parsing of configuration files. - [EXTERNAL_DOWNLOADS]: Interacts with GitHub's API to fetch review status and repository settings. This interaction targets a well-known service and is necessary for verifying the deployment history and enforcing security policies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository metadata that could potentially be influenced by external actors.
- Ingestion points: Pull request numbers and review counts retrieved from the GitHub API in
SKILL.md. - Boundary markers: None present in the shell command interpolations.
- Capability inventory: File reads, repository configuration updates via
gh api, and shell script execution. - Sanitization: The skill uses
jqto extract specific structured fields (numbers and logins), which prevents raw untrusted data from directly influencing the structure of subsequent commands.
Audit Metadata