netlify-ai-gateway
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing several official Node.js packages via npm, including
openai,@anthropic-ai/sdk,@google/genai,@openrouter/sdk, and@netlify/vite-pluginfor project integration. - [COMMAND_EXECUTION]: The documentation includes standard operational commands for the Netlify CLI, such as
netlify dev,netlify init, andnetlify deploy, which are necessary for local development and deployment to the vendor's platform. - [INDIRECT_PROMPT_INJECTION]: The skill describes use cases involving the processing of untrusted data, specifically mentioning the summarization of form submissions.
- Ingestion points: Netlify Functions (e.g.,
netlify/functions/joke.js) that process external inputs or form data. - Boundary markers: The minimal code examples do not demonstrate the use of delimiters or 'ignore' instructions for data processed by the LLM.
- Capability inventory: The skill demonstrates network communication with AI provider APIs via official SDKs.
- Sanitization: The provided illustrative code snippets do not include input validation or sanitization logic for external content.
Audit Metadata