ai-sdk
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches updated model lists and documentation from official Vercel domains (ai-sdk.dev and vercel.sh). These are well-known services provided by the platform vendor.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external documentation and local source code for grounding.
- Ingestion points: local
node_modules/ai/directory and theai-sdk.devremote documentation site. - Boundary markers: Absent.
- Capability inventory: Shell command execution for searching (
rg) and fetching data (curl). - Sanitization: Absent.
- Context: This behavior is the primary intended purpose of the skill to provide accurate technical assistance.- [COMMAND_EXECUTION]: Provides instructions for using standard command-line tools like
rg(ripgrep) andcurlto inspect project files and query official APIs. These operations are scoped to project-relevant directories and trusted endpoints.
Audit Metadata