genkit
Build Firebase Genkit AI Workflows
Developers need clear patterns for production AI flows, agents, RAG, and deployment. This skill provides Genkit setup, examples, commands, and deployment guidance for Firebase and Cloud Run.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "genkit" from https://skillstore.io/skills/supercent-io-genkit.md and its manifest at https://skillstore.io/api/skills/supercent-io-genkit/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "genkit". Create a starter Genkit flow for summarizing support tickets.
Expected outcome:
A concise implementation plan with fields for ticket text, priority, summary, and next action, plus local test commands.
Using "genkit". Design a RAG assistant for product documentation.
Expected outcome:
A pipeline outline covering document indexing, retrieval limits, grounded answer rules, evaluation inputs, and deployment choices.
Using "genkit". Prepare my flow for Cloud Run deployment.
Expected outcome:
A deployment checklist covering server handler setup, environment variables, region choice, and post-deploy verification.
Security Audit
CriticalMost static findings are false positives caused by Markdown code fences, inline backticks, documentation links, and placeholder secret names. The confirmed issue is the curl-to-bash installer pattern in SKILL.md and SKILL.toon, which executes remote code without verification. No prompt injection attempt or credential exfiltration intent was found in the reviewed files.
Confirmed security concerns (2)
Risk Factors
⚙️ External commands (76)
🌐 Network access (13)
🔑 Env variables (6)
Detected Patterns
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/supercent-io-genkit/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/supercent-io-genkit?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/supercent-io-genkit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/supercent-io-genkit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/supercent-io-genkit.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
supercent-io. (2026). genkit security audit report (audit version 4) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/supercent-io-genkit/audits/4BibTeX citation
@techreport{supercent-io-supercent-io-genkit-2026,
author = {supercent-io},
title = {genkit security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/supercent-io-genkit/audits/4},
note = {Author version 1.0.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "genkit security audit report (audit version 4)"
version: "1.0.0"
type: report
authors:
- name: "supercent-io"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/supercent-io-genkit/audits/4"
identifiers:
- type: other
value: "skillstore:supercent-io-genkit:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Create a typed AI endpoint
Build a Genkit flow with validated inputs, structured outputs, and traceable execution.
Prototype a retrieval assistant
Combine vector retrieval, grounding instructions, and a Genkit flow for question answering.
Prepare cloud deployment
Map a working local flow to Firebase Functions, Express, or Cloud Run deployment patterns.
Try These Prompts
Help me create a Firebase Genkit TypeScript flow for <task>. Include input fields, output shape, and local test steps.
Update my Genkit flow to stream progress for <use case>. Explain the stream schema, final output, and client handling.
Design a Genkit agent for <goal> using tools for <tool list>. Include schemas, tool behavior, and error handling.
Plan a Genkit RAG pipeline for <content source>. Cover indexing, retrieval, grounding, evaluation, secrets, and Firebase or Cloud Run deployment.
Best Practices
- Define schemas for every flow input and output before adding model calls.
- Use secret managers or environment variables for provider keys, and avoid logging secret values.
- Test flows in the Genkit Developer UI before deploying them to shared environments.
Avoid
- Do not run installation or deployment commands without reviewing the command and target environment.
- Do not hardcode API keys, project IDs, or private endpoints into shared examples.
- Do not let agent tools call external services without validation, timeouts, and clear user consent.
Frequently Asked Questions
What does this skill help me build?
Does it support model providers beyond Gemini?
Can it deploy code for me automatically?
Is it useful for RAG applications?
How should API keys be handled?
Which tools can use this skill?
Developer Details
Author
supercent-ioLicense
MIT
Author version
v1.0.0
Skillstore revision
r1
Ref
f93e9bb0daca99badb6a7e574b97737155d57cb3
Maintenance freshness
7/18/2026
Usage
6 downloads · 145 views
File structure
📄 SKILL.md