coderabbit-deploy-integration
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a set of configuration templates and automation scripts for organization-wide deployment of a legitimate third-party service (CodeRabbit). All external references point to official documentation and application pages.
- [COMMAND_EXECUTION]: The instructions include Bash scripts intended to be run by the agent or user to automate PR creation (
gh pr create) and branch protection updates (gh api .../protection). These scripts use the tools specified in the skill'sallowed-toolsmetadata and follow standard DevOps automation patterns. - [INDIRECT_PROMPT_INJECTION]: The shell scripts ingest repository names into variables used in shell commands. While this creates a potential surface for injection if the agent were to populate these lists from untrusted external sources, the skill itself provides safe templates for administrative use.
- Ingestion points: The
REPOSarray andORGvariable in the Bash scripts provided in Step 4 and Step 5. - Boundary markers: Absent (typical for configuration templates).
- Capability inventory: GitHub CLI (
gh), Git (git), and local file system management (mktemp,cp,rm). - Sanitization: Not present within the script templates; the system relies on the user or agent providing valid repository strings.
Audit Metadata