You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
> Podman is a drop-in replacement for`docker` which can also be usedin these commands.
99
+
> [!Tip]
100
+
> Podman is a drop-in replacement for`docker` which can also be usedin these commands.
103
101
104
-
3. Run you container
102
+
3. Run your container
105
103
106
104
```bash
107
105
podman run -p 10001:10001 -e GOOGLE_API_KEY=your_api_key_here crewai-a2a-server
@@ -110,8 +108,9 @@ Agent can also be built using a container file.
110
108
4. Run A2A client (follow step 5 from the section above)
111
109
112
110
> [!Important]
113
-
>***Access URL:** You must access the A2A client through the URL `0.0.0.0:10001`. Using `localhost` will not work.
114
-
>***Hostname Override:** If you're deploying to an environment where the hostname is defined differently outside the container, use the `HOST_OVERRIDE` environment variable to set the expected hostname on the Agent Card. This ensures proper communication with your client application.
111
+
>
112
+
> - **Access URL:** You must access the A2A client through the URL `0.0.0.0:10001`. Using `localhost` will not work.
113
+
> - **Hostname Override:** If you're deploying to an environment where the hostname is defined differently outside the container, use the `HOST_OVERRIDE` environment variable to set the expected hostname on the Agent Card. This ensures proper communication with your client application.
115
114
116
115
## Features & Improvements
117
116
@@ -130,14 +129,6 @@ Agent can also be built using a container file.
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.
140
-
141
-
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.
142
-
143
-
Developers are responsible for implementing appropriate security measures, such as input validation and secure handling of credentials to protect their systems and users.
0 commit comments