aiskillstore/marketplace / skills/aayushbaniya2006/ai-sdk-handler
ai-sdk-handler
VerifiedIntegrate Vercel AI SDK for LLMs, Chatbots, Generative UI, and Agentic Workflows.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.0 KB |
| examples.md | markdown | 7.2 KB |
| reference.md | markdown | 5.4 KB |
| skill-report.json | config | 43.7 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-05T00:30:36.901Z",
"slug": "aayushbaniya2006-ai-sdk-handler",
"source_url": "https://github.com/AayushBaniya2006/blinkfund/tree/main/.claude/skills/ai-sdk-handler",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "da1bf25b1bef0ea285912765d2ccb88012584fe44ebbf291210897d8507f26bc",
"tree_hash": "cb9d640c3d254bb639beee02c583c01410405d661a55db18411325202efaebd4",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "ai-sdk-handler",
"description": "Build Vercel AI SDK features for streaming chat, structured output, generative UI, and Inngest-backed agent workflows.",
"summary": "Guides Next.js teams through Vercel AI SDK chat, structured generation, generative UI, and agent workflows.",
"icon": "📦",
"version": "1.0.0",
"author": "AayushBaniya2006",
"license": "MIT",
"tags": [
"vercel-ai-sdk",
"nextjs",
"llm",
"chatbots",
"agents"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"env_access"
],
"category": "coding"
},
"security_audit": {
"risk_level": "high",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "The static command findings are false positives caused by Markdown inline code and TypeScript template literals, not shell execution. The API key findings are also false positives because the examples read provider keys from server-side environment variables rather than hardcoding or leaking secrets. I found semantic risks in unauthenticated AI route examples and missing prompt-injection guardrail guidance.",
"remediation": [
{
"issue": "Some AI route examples omit authentication.",
"suggestion": "Update every route example to wrap handlers with withAuthRequired or clearly mark unauthenticated snippets as non-production examples.",
"severity": "high"
},
{
"issue": "Prompt injection and data minimization guidance is missing.",
"suggestion": "Add guidance for validating user input, separating system instructions from user data, redacting secrets, and limiting tool permissions.",
"severity": "medium"
},
{
"issue": "Provider API key examples lack an explicit server-only warning.",
"suggestion": "Add a short note that provider keys must stay server-side and must never be exposed to client components or logs.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "examples.md",
"line_start": 141,
"line_end": 152
},
{
"file": "examples.md",
"line_start": 152,
"line_end": 155
},
{
"file": "examples.md",
"line_start": 155,
"line_end": 166
},
{
"file": "examples.md",
"line_start": 166,
"line_end": 174
},
{
"file": "reference.md",
"line_start": 41,
"line_end": 47
},
{
"file": "reference.md",
"line_start": 72,
"line_end": 73
},
{
"file": "reference.md",
"line_start": 73,
"line_end": 87
},
{
"file": "reference.md",
"line_start": 146,
"line_end": 151
},
{
"file": "reference.md",
"line_start": 173,
"line_end": 183
},
{
"file": "reference.md",
"line_start": 183,
"line_end": 191
},
{
"file": "SKILL.md",
"line_start": 11,
"line_end": 11
},
{
"file": "SKILL.md",
"line_start": 14,
"line_end": 14
},
{
"file": "SKILL.md",
"line_start": 15,
"line_end": 15
},
{
"file": "SKILL.md",
"line_start": 16,
"line_end": 16
},
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 23
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 24
},
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 29
},
{
"file": "SKILL.md",
"line_start": 34,
"line_end": 34
},
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 39
},
{
"file": "SKILL.md",
"line_start": 50,
"line_end": 50
},
{
"file": "SKILL.md",
"line_start": 51,
"line_end": 51
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 59
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "reference.md",
"line_start": 179,
"line_end": 179
},
{
"file": "SKILL.md",
"line_start": 45,
"line_end": 45
}
]
},
{
"factor": "env_access",
"evidence": [
{
"file": "reference.md",
"line_start": 13,
"line_end": 13
},
{
"file": "reference.md",
"line_start": 17,
"line_end": 17
},
{
"file": "reference.md",
"line_start": 13,
"line_end": 13
},
{
"file": "reference.md",
"line_start": 17,
"line_end": 17
},
{
"file": "reference.md",
"line_start": 13,
"line_end": 13
},
{
"file": "reference.md",
"line_start": 17,
"line_end": 17
}
]
}
],
"static_findings": [
{
"id": "external_commands:examples.md:141:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "examples.md",
"line_start": 141,
"line_end": 152,
"snippet": "prompt: `Create a step-by-step research plan for: ${topic}`,"
},
{
"id": "external_commands:examples.md:152:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "examples.md",
"line_start": 152,
"line_end": 155,
"snippet": "const finding = await step.run(`execute-step-${i}`, async () => {"
},
{
"id": "external_commands:examples.md:155:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "examples.md",
"line_start": 155,
"line_end": 166,
"snippet": "prompt: `Execute research step: ${steps[i]}`,"
},
{
"id": "external_commands:examples.md:166:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "examples.md",
"line_start": 166,
"line_end": 174,
"snippet": "prompt: `Synthesize these findings into a report:\\n${findings.join('\\n\\n')}`,"
},
{
"id": "external_commands:reference.md:41:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "reference.md",
"line_start": 41,
"line_end": 47,
"snippet": "console.log(`User ${session.user.id} used ${usage.totalTokens} tokens.`);"
},
{
"id": "external_commands:reference.md:72:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "reference.md",
"line_start": 72,
"line_end": 73,
"snippet": "<div key={m.id} className={`mb-4 ${m.role === 'user' ? 'text-right' : 'text-left'}`}>"
},
{
"id": "external_commands:reference.md:73:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "reference.md",
"line_start": 73,
"line_end": 87,
"snippet": "<div className={`inline-block p-2 rounded-lg ${m.role === 'user' ? 'bg-blue-100' : 'bg-gray-100'}`}>"
},
{
"id": "external_commands:reference.md:146:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "reference.md",
"line_start": 146,
"line_end": 151,
"snippet": "prompt: `Create a day trip itinerary for ${destination}`,"
},
{
"id": "external_commands:reference.md:173:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "reference.md",
"line_start": 173,
"line_end": 183,
"snippet": "prompt: `Create a research plan for: ${topic}`"
},
{
"id": "external_commands:reference.md:183:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "reference.md",
"line_start": 183,
"line_end": 191,
"snippet": "prompt: `Summarize this plan: ${plan}`"
},
{
"id": "network:reference.md:179:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "reference.md",
"line_start": 179,
"line_end": 179,
"snippet": "// See: https://ai-sdk.dev/docs/agents/loop-control"
},
{
"id": "env_access:reference.md:13:environment-variable-access-dot-notation",
"category": "env_access",
"severity": "low",
"pattern": "Environment variable access (dot notation)",
"file": "reference.md",
"line_start": 13,
"line_end": 13,
"snippet": "apiKey: process.env.OPENAI_API_KEY,"
},
{
"id": "env_access:reference.md:17:environment-variable-access-dot-notation",
"category": "env_access",
"severity": "low",
"pattern": "Environment variable access (dot notation)",
"file": "reference.md",
"line_start": 17,
"line_end": 17,
"snippet": "apiKey: process.env.ANTHROPIC_API_KEY,"
},
{
"id": "env_access:reference.md:13:environment-variable-object",
"category": "env_access",
"severity": "low",
"pattern": "Environment variable object",
"file": "reference.md",
"line_start": 13,
"line_end": 13,
"snippet": "apiKey: process.env.OPENAI_API_KEY,"
},
{
"id": "env_access:reference.md:17:environment-variable-object",
"category": "env_access",
"severity": "low",
"pattern": "Environment variable object",
"file": "reference.md",
"line_start": 17,
"line_end": 17,
"snippet": "apiKey: process.env.ANTHROPIC_API_KEY,"
},
{
"id": "env_access:reference.md:13:generic-api-secret-keys",
"category": "env_access",
"severity": "high",
"pattern": "Generic API/secret keys",
"file": "reference.md",
"line_start": 13,
"line_end": 13,
"snippet": "apiKey: process.env.OPENAI_API_KEY,"
},
{
"id": "env_access:reference.md:17:generic-api-secret-keys",
"category": "env_access",
"severity": "high",
"pattern": "Generic API/secret keys",
"file": "reference.md",
"line_start": 17,
"line_end": 17,
"snippet": "apiKey: process.env.ANTHROPIC_API_KEY,"
},
{
"id": "sensitive:reference.md:13:environment-file-access",
"category": "sensitive",
"severity": "high",
"pattern": "Environment file access",
"file": "reference.md",
"line_start": 13,
"line_end": 13,
"snippet": "apiKey: process.env.OPENAI_API_KEY,"
},
{
"id": "sensitive:reference.md:17:environment-file-access",
"category": "sensitive",
"severity": "high",
"pattern": "Environment file access",
"file": "reference.md",
"line_start": 17,
"line_end": 17,
"snippet": "apiKey: process.env.ANTHROPIC_API_KEY,"
},
{
"id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 11,
"line_end": 11,
"snippet": "**Note**: For Image/Video generation (Replicate, Fal.ai), continue to use `ai-handler`. Use `ai-sdk-"
},
{
"id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 14,
"line_end": 14,
"snippet": "- **Chatbots**: Building interactive chat interfaces (`useChat`, `streamText`)."
},
{
"id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 15,
"line_end": 15,
"snippet": "- **Structured Data**: Extracting JSON from text (`generateObject`)."
},
{
"id": "external_commands:SKILL.md:16:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 16,
"line_end": 16,
"snippet": "- **Generative UI**: Streaming React components directly from the server (`streamUI`)."
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 23,
"line_end": 23,
"snippet": "- **Tool**: `streamText` (Server), `useChat` (Client)."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 24,
"snippet": "- **Pattern**: Create a route handler at `src/app/api/chat/route.ts`."
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 25,
"line_end": 25,
"snippet": "- **Auth**: Wrap with `withAuthRequired` to protect the route."
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 26,
"line_end": 26,
"snippet": "- **UI**: Use `src/components/chat-ui/` for chat components."
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 29,
"line_end": 29,
"snippet": "- **Tool**: `streamUI` (Server)."
},
{
"id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 34,
"line_end": 34,
"snippet": "- **Tool**: `generateObject`."
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 39,
"line_end": 39,
"snippet": "- **Tool**: `generateText` / `generateObject` inside Inngest steps."
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 50,
"line_end": 50,
"snippet": "2. **Auth**: Never expose open AI routes. Always verify `session.user.id`."
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 51,
"line_end": 51,
"snippet": "3. **Providers**: Use `@ai-sdk/openai` or `@ai-sdk/anthropic`. Abstract the provider configuration "
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 52,
"snippet": "4. **Backpressure**: The AI SDK handles this automatically in `streamText`."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 53,
"line_end": 53,
"snippet": "5. **Caching**: Use `unstable_cache` or KV stores if queries are repetitive."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 58,
"line_end": 58,
"snippet": "- **`reference.md`**: Core setup and essential code snippets."
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 59,
"line_end": 59,
"snippet": "- **`examples.md`**: Exhaustive examples covering:"
},
{
"id": "network:SKILL.md:45:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 45,
"line_end": 45,
"snippet": "4. **Docs**: [AI SDK Agents](https://ai-sdk.dev/docs/agents/overview)."
}
],
"finding_verdicts": [
{
"id": "external_commands:examples.md:141:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript example text using template literals for AI prompts or Inngest step names. It does not execute a shell command or spawn an external process."
},
{
"id": "external_commands:examples.md:152:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript example text using template literals for AI prompts or Inngest step names. It does not execute a shell command or spawn an external process."
},
{
"id": "external_commands:examples.md:155:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript example text using template literals for AI prompts or Inngest step names. It does not execute a shell command or spawn an external process."
},
{
"id": "external_commands:examples.md:166:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript example text using template literals for AI prompts or Inngest step names. It does not execute a shell command or spawn an external process."
},
{
"id": "external_commands:reference.md:41:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript or JSX example text using template literals for logging, CSS class names, or AI prompts. It is not Ruby or shell backtick execution."
},
{
"id": "external_commands:reference.md:72:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript or JSX example text using template literals for logging, CSS class names, or AI prompts. It is not Ruby or shell backtick execution."
},
{
"id": "external_commands:reference.md:73:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript or JSX example text using template literals for logging, CSS class names, or AI prompts. It is not Ruby or shell backtick execution."
},
{
"id": "external_commands:reference.md:146:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript or JSX example text using template literals for logging, CSS class names, or AI prompts. It is not Ruby or shell backtick execution."
},
{
"id": "external_commands:reference.md:173:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript or JSX example text using template literals for logging, CSS class names, or AI prompts. It is not Ruby or shell backtick execution."
},
{
"id": "external_commands:reference.md:183:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This is TypeScript or JSX example text using template literals for logging, CSS class names, or AI prompts. It is not Ruby or shell backtick execution."
},
{
"id": "network:reference.md:179:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The URL is a documentation link to ai-sdk.dev in Markdown comments or prose. It is not runtime network code and does not exfiltrate data."
},
{
"id": "env_access:reference.md:13:environment-variable-access-dot-notation",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "env_access:reference.md:17:environment-variable-access-dot-notation",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "env_access:reference.md:13:environment-variable-object",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "env_access:reference.md:17:environment-variable-object",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "env_access:reference.md:13:generic-api-secret-keys",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "env_access:reference.md:17:generic-api-secret-keys",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "sensitive:reference.md:13:environment-file-access",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "sensitive:reference.md:17:environment-file-access",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The snippet reads provider API keys from server-side environment variables in a configuration example. It does not hardcode, print, or transmit secrets outside the AI provider setup."
},
{
"id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:16:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This appears in Markdown prose or inline code names inside the skill instructions. Backticks are documentation formatting, not executable shell syntax."
},
{
"id": "network:SKILL.md:45:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The URL is a documentation link to ai-sdk.dev in Markdown comments or prose. It is not runtime network code and does not exfiltrate data."
}
],
"semantic_findings": [
{
"title": "Public AI Route Examples Lack Authentication",
"description": "Several route examples read request bodies and call model APIs without wrapping the handler in authentication. Copying these examples directly can expose paid AI endpoints to unauthenticated use.",
"severity": "high",
"locations": [
{
"file": "examples.md",
"line_start": 17,
"line_end": 23
},
{
"file": "examples.md",
"line_start": 63,
"line_end": 68
},
{
"file": "examples.md",
"line_start": 101,
"line_end": 114
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 51
}
],
"confidence": 0.86,
"confidence_reasoning": "The examples show public POST handlers that call model APIs, while the skill separately says AI routes should verify session.user.id. This is a concrete copy-paste production risk, although the examples are documentation snippets."
},
{
"title": "Prompt Injection Guardrails Are Not Shown",
"description": "Examples pass user-controlled messages, prompts, destinations, and agent topics into model calls without input boundaries or safety guidance. This can teach unsafe patterns for prompt-injection-prone workflows.",
"severity": "medium",
"locations": [
{
"file": "examples.md",
"line_start": 17,
"line_end": 23
},
{
"file": "examples.md",
"line_start": 101,
"line_end": 114
},
{
"file": "examples.md",
"line_start": 135,
"line_end": 166
},
{
"file": "reference.md",
"line_start": 134,
"line_end": 147
}
],
"confidence": 0.74,
"confidence_reasoning": "The code is educational, but multiple snippets send untrusted request or event data directly into model prompts. I found no countervailing guidance on prompt injection, data minimization, or policy boundaries."
}
],
"critical_findings": [],
"high_findings": [
{
"title": "Public AI Route Examples Lack Authentication",
"description": "Several route examples read request bodies and call model APIs without wrapping the handler in authentication. Copying these examples directly can expose paid AI endpoints to unauthenticated use.",
"locations": [
{
"file": "examples.md",
"line_start": 17,
"line_end": 23
},
{
"file": "examples.md",
"line_start": 63,
"line_end": 68
},
{
"file": "examples.md",
"line_start": 101,
"line_end": 114
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 51
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.86,
"confidence_reasoning": "The examples show public POST handlers that call model APIs, while the skill separately says AI routes should verify session.user.id. This is a concrete copy-paste production risk, although the examples are documentation snippets."
}
],
"medium_findings": [
{
"title": "Prompt Injection Guardrails Are Not Shown",
"description": "Examples pass user-controlled messages, prompts, destinations, and agent topics into model calls without input boundaries or safety guidance. This can teach unsafe patterns for prompt-injection-prone workflows.",
"locations": [
{
"file": "examples.md",
"line_start": 17,
"line_end": 23
},
{
"file": "examples.md",
"line_start": 101,
"line_end": 114
},
{
"file": "examples.md",
"line_start": 135,
"line_end": 166
},
{
"file": "reference.md",
"line_start": 134,
"line_end": 147
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The code is educational, but multiple snippets send untrusted request or event data directly into model prompts. I found no countervailing guidance on prompt injection, data minimization, or policy boundaries."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 3,
"total_lines": 553,
"audit_model": "codex",
"audited_at": "2026-07-05T00:30:36.901Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Build Vercel AI SDK Workflows",
"value_statement": "Teams often lose time connecting chat, structured output, and agent workflows across Next.js services. This skill provides focused Vercel AI SDK patterns for Claude, Codex, and Claude Code users.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"Vercel AI SDK",
"AI SDK handler",
"Next.js AI",
"streamText",
"useChat",
"generateObject",
"Inngest agents"
],
"actual_capabilities": [
"Explains when to use the Vercel AI SDK for chat, structured output, generative UI, and agents.",
"Provides Next.js route handler examples for streamText, streamUI, and generateObject.",
"Shows OpenAI and Anthropic provider setup using server-side environment variables.",
"Demonstrates an Inngest background agent workflow with fixed loop control.",
"Includes client chat patterns using useChat and streaming data."
],
"limitations": [
"The examples are documentation snippets, not a complete application scaffold.",
"Some example routes need authentication before production use.",
"It does not cover image or video generation workflows.",
"It assumes Next.js App Router, React, Zod, and Inngest conventions."
],
"use_cases": [
{
"title": "Add Streaming Chat",
"description": "Create a protected chat route and React client that stream model responses to users.",
"target_user": "Full-stack developers"
},
{
"title": "Extract Structured Output",
"description": "Use Zod schemas and generateObject to convert user input into typed application data.",
"target_user": "Product engineers"
},
{
"title": "Run Background Agents",
"description": "Move long-running research or planning tasks into Inngest workflows with bounded steps.",
"target_user": "Platform engineers"
}
],
"prompt_templates": [
{
"title": "Add Basic Chat",
"scenario": "Beginner setup for a new chat feature.",
"prompt": "Use this skill to add an authenticated Vercel AI SDK streaming chat route and matching React client component to my Next.js app."
},
{
"title": "Generate Structured Data",
"scenario": "Intermediate task for typed extraction.",
"prompt": "Use this skill to create a generateObject endpoint that validates the output with a Zod schema and returns typed application data."
},
{
"title": "Create Generative UI",
"scenario": "Advanced interface pattern with server-rendered components.",
"prompt": "Use this skill to design a streamUI route that returns React components from tool calls and keeps all tools server-side."
},
{
"title": "Design Agent Workflow",
"scenario": "Advanced background workflow with operational safeguards.",
"prompt": "Use this skill to design an Inngest research agent with authentication, rate limits, bounded loops, schema validation, and persisted results."
}
],
"output_examples": [
{
"input": "Create an authenticated streaming chat feature for a Next.js app.",
"output": "A short implementation plan covering provider setup, a protected POST route, a useChat client, and deployment checks."
},
{
"input": "Build a structured itinerary generator from user input.",
"output": [
"A suggested schema for itinerary fields.",
"A route design using generateObject.",
"Validation and error handling notes for production use."
]
},
{
"input": "Move a multi-step research task into a background agent.",
"output": "A workflow outline with Inngest triggers, fixed step limits, model calls, result storage, and user notification points."
}
],
"best_practices": [
"Protect every AI API route with authentication and per-user rate limits.",
"Keep provider keys in server-only environment variables.",
"Use schemas and loop limits for structured output and agents."
],
"anti_patterns": [
"Do not copy unauthenticated examples into production routes.",
"Do not send secrets, raw logs, or private user data into prompts.",
"Do not run unbounded agent loops without timeout and step limits."
],
"faq": [
{
"question": "What does this skill help build?",
"answer": "It helps build Vercel AI SDK features such as streaming chat, structured output, generative UI, and background agents."
},
{
"question": "Which coding assistants can use it?",
"answer": "The report marks support for Claude, Codex, and Claude Code."
},
{
"question": "Does it install dependencies automatically?",
"answer": "No. It documents package names and code patterns that a developer can apply in a project."
},
{
"question": "Is it production ready as written?",
"answer": "It is a starting point. Add authentication, rate limits, logging, monitoring, and privacy review before production use."
},
{
"question": "Does it cover image or video generation?",
"answer": "No. The skill says to use ai-handler for Replicate or Fal.ai media generation workflows."
},
{
"question": "Which frameworks does it assume?",
"answer": "It assumes Next.js App Router, React, the Vercel AI SDK, Zod, and optional Inngest workflows."
}
]
},
"file_structure": [
{
"name": "examples.md",
"type": "file",
"path": "examples.md",
"lines": 291
},
{
"name": "reference.md",
"type": "file",
"path": "reference.md",
"lines": 193
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 69
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |