deploy-vue
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill references a sensitive file path at ~/.build-host/credentials.json to guide the agent in locating authentication credentials. This is consistent with the intended use of the developer's platform and includes explicit instructions not to leak these secrets in logs or chat.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it operates on user-provided project directories and git repositories. 1. Ingestion points: The project directory or git repository to operate on. 2. Boundary markers: Absent from the instructions. 3. Capability inventory: The skill utilizes network operations (GET/POST) to communicate with the build.host API for deployment and monitoring. 4. Sanitization: The instructions do not specify content sanitization for processed project data.
Audit Metadata