ai-orchestration-vercel-ai-sdk

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user prompts and external tool outputs (e.g., web search results, weather data) by interpolating them directly into LLM prompts, creating a potential surface for indirect instruction execution.
  • Ingestion points: External data enters the agent context via variables such as article in examples/core.md, topic in examples/structured-output.md, and relevantChunks in examples/rag.md.
  • Boundary markers: Most examples lack robust delimiters or explicit instructions to ignore embedded commands, often relying on simple labels like Context: or Article:.
  • Capability inventory: The skill facilitates network operations through the fetch API in tool definitions (e.g., examples/tools.md) and manages external tool execution flows.
  • Sanitization: No explicit sanitization or filtering of external content is shown before it is interpolated into model prompts.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing standard packages from the Vercel AI SDK ecosystem and the Zod validation library from public registries.
  • Evidence: References to ai, @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/google, @ai-sdk/react, and zod are found throughout reference.md and various code examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:56 PM
Security Audit — agent-trust-hub — ai-orchestration-vercel-ai-sdk