grammarly-ci-integration
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a GitHub Actions workflow that utilizes standard environment variables and secrets to handle Grammarly API credentials, adhering to security best practices.
- [SAFE]: The provided TypeScript tests demonstrate the use of mocking for the Grammarly service, which prevents unnecessary network traffic and protects API keys during unit testing.
- [SAFE]: The documentation includes comprehensive prerequisites and error-handling guidance focused on credential rotation and branch protection.
- [INDIRECT_PROMPT_INJECTION]: The skill integrates with text analysis services, which constitutes a surface for processing untrusted data.
- Ingestion points: External text inputs are processed by the checkDocumentation function and Grammarly integration tests in SKILL.md.
- Boundary markers: Instructions explicitly require the use of fictional fixtures and sandbox targets to maintain data isolation.
- Capability inventory: The skill is granted Read, Write, Edit, and Bash(gh:*) capabilities for pipeline management.
- Sanitization: The workflow incorporates policy checks and manual review steps for canary promotions to validate process integrity.
Audit Metadata