ai-gateway
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and configuration patterns for Vercel AI Gateway, a legitimate and well-known service from Vercel.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation and resources from Vercel and the AI SDK, which are recognized as well-known service providers.
- [COMMAND_EXECUTION]: Provides standard shell commands for project initialization and environment management such as
vercel env pullandnpm installfor required dependencies. - [PROMPT_INJECTION]:
- Ingestion points: The skill templates ingest untrusted data via the
userMessagevariable into AI model prompts (SKILL.md). - Boundary markers: No explicit delimiters are present in the provided code examples to separate user-supplied content from system instructions.
- Capability inventory: The skill facilitates network-based interactions with AI model providers through the AI Gateway.
- Sanitization: No methods for sanitizing or validating user input are described in the guidance provided.
Audit Metadata