Add Admin API Endpoint
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as documentation and a template for developers working with the Ghost CMS codebase. It does not contain malicious instructions, obfuscated code, or unauthorized data access patterns.
- [COMMAND_EXECUTION]: The skill includes instructions to run local test commands using
yarn test:single. This is a standard part of the development and verification process within a local repository and does not involve executing untrusted remote code. - [PROMPT_INJECTION]: The instructions are purely technical and instructional, with no attempts to manipulate the agent's behavior, bypass safety guardrails, or extract system prompts.
- [DATA_EXFILTRATION]: No evidence of hardcoded credentials, secrets, or network operations targeting non-whitelisted domains was found. Example identifiers used in the documentation are clearly generic placeholders.
- [EXTERNAL_DOWNLOADS]: The skill references standard library packages associated with the Ghost project (e.g.,
@tryghost/api-framework) as part of its development instructions but does not perform any remote downloads during execution.
Audit Metadata