This sample agent can be used to proof-read and polish content. The provided sample is built using Genkit using the Gemini API.
- Access to an LLM and API Key
-
Navigate to the samples directory:
cd samples/js -
Create an environment file with your API key:
echo "GOOGLE_API_KEY=your_api_key_here" > .env
-
Run npm install:
npm install
-
Run the Content Editor Agent
NOTE: By default, the agent will start on port 10003. To override this, use
export CONTENT_EDITOR_AGENT_PORT=YOUR_PORT.npm run agents:content-editor
-
In a separate terminal, run the A2A client and use it to send a message to the agent:
npm run a2a:cli
-
To make use of this agent in a content creation multi-agent system, check out the content_creation sample.
Important: The sample code provided is for demonstration purposes and illustrates the mechanics of the Agent-to-Agent (A2A) protocol. When building production applications, it is critical to treat any agent operating outside of your direct control as a potentially untrusted entity.
All data received from an external agent—including but not limited to its AgentCard, messages, artifacts, and task statuses—should be handled as untrusted input. For example, a malicious agent could provide an AgentCard containing crafted data in its fields (e.g., description, name, skills.description). If this data is used without sanitization to construct prompts for a Large Language Model (LLM), it could expose your application to prompt injection attacks. Failure to properly validate and sanitize this data before use can introduce security vulnerabilities into your application.
Developers are responsible for implementing appropriate security measures, such as input validation and secure handling of credentials to protect their systems and users.