ai-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches current model information from the official Vercel AI Gateway at
https://ai-gateway.vercel.sh/v1/models. This ensures the agent uses the latest versions of models like Claude and GPT. - [COMMAND_EXECUTION]: Uses standard shell utilities like
grepto search the localnode_modules/ai/directory andcurlto query official APIs. These operations are restricted to searching documentation and fetching model metadata. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest documentation from local source files and the official
https://ai-sdk.devwebsite. This ingestion is the intended primary purpose of the skill to overcome outdated training data.
Audit Metadata