Add A2AS Certificate

[a2as-team]

Add A2AS Certificate for Agent Transparency and Security

Summary

This PR adds an agent certificate using the A2AS format - an open standard for agentic AI security. The certificate declares operational boundaries, agentic actions, and resources. It acts as a transparency artifact for your agent.

This repository has been certified and added to the registry.

Info and visualization available via the link or badge:

A2AS.org/certified/agents/fmind/slides-translator-agent

About A2AS Certificates

A2AS certificates are declarative manifests for agent behavior. They describe what an agent is designed to do:

• AI level: agents, models, tools, resources
• APP level: imports, functions, variables
• OS level: files, networks, processes

Certificates are human-readable and machine-readable, and can be used as a transparency and security artifact.

The A2AS standard is a project from the A2AS.org initiative led by experts from big tech and security companies.

Benefits For This Project

This A2AS certificate can help to:

• Make it easier for contributors to see what the agent does
• Increase trust in your agent by making its behavior explicit
• Grow adoption with security-conscious and enterprise users

What This PR Does

This PR doesn't change any code:

• Only adds a2as.yaml to the repository root
• Aligns the certificate with the current agent logic
• Does not modify agent code, prompts, or configuration

Optional Next Steps

When the agent changes, the A2AS certificate is expected to be updated.

A2AS project maintainers can help with updating the certificate as your agent evolves.

If you find this relevant, you can add the A2AS Shield to your README.md file:

[gemini-code-assist]

Summary of Changes

Hello @a2as-team, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces an A2AS certificate to enhance transparency and security for the agent. This certificate, defined in a new a2as.yaml file, explicitly outlines the agent's behavior, including its AI level, application-level interactions, and OS-level resource usage. This initiative aims to increase trust, facilitate understanding for contributors, and potentially boost adoption among security-conscious users without altering any existing agent code or configuration.

Highlights

• A2AS Certificate Addition: A new a2as.yaml file has been added to the repository root, providing an Agent to Agent Security (A2AS) certificate. This certificate acts as a transparency artifact, declaring the agent's operational boundaries, actions, and resources.
• Enhanced Transparency and Security: The A2AS certificate explicitly outlines the agent's behavior, including its AI level, application-level interactions, and OS-level resource usage, aiming to increase trust and facilitate understanding for contributors.
• No Code Changes: This pull request solely focuses on adding the a2as.yaml file and does not modify any existing agent code, prompts, or configuration.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• a2as.yaml
  • Added a new A2AS certificate manifest for the fmind/slides-translator-agent.
  • Defined the agent's type, models used (gemini-2.5-flash), and primary tool (translate_presentation).
  • Detailed the agent's instructions, interaction flow, and error handling.
  • Listed various imports, functions, environment variables, file access patterns, and network interactions.

Activity

• No human activity (comments, reviews, etc.) has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces an A2AS certificate for the agent, which is a great step towards transparency and security. The certificate (a2as.yaml) provides a declarative manifest of the agent's behavior. My review focuses on ensuring the correctness and consistency of this new manifest file. I've found a few minor inconsistencies between the certificate and the agent's implementation that should be addressed: an incorrect data type for the temperature parameter, a misrepresentation of a hardcoded constant as an environment variable, and an issuance timestamp set to a future date. Please see the detailed comments for suggestions on how to fix these.

[gemini-code-assist]

The issued.at timestamp is set to a future date ('2026-02-11T16:45:30Z'). The issuance timestamp should reflect when the certificate was created, not a future date. Please correct this to the actual issuance date and time.

[gemini-code-assist]

The temperature value is specified as a string "0.0". Based on the google.genai.types.GenerateContentConfig class and its usage in slides_translator_agent/agent.py, this parameter should be a float. Please remove the quotes to make it a numeric type.

        temperature: 0.0

[gemini-code-assist]

The TOKEN_URL is declared as an environment variable (type: env), but in the codebase (slides_translator_agent/auths.py, line 14), it is hardcoded as a constant: TOKEN_URL = "https://oauth2.googleapis.com/token". This part of the manifest misrepresents the agent's configuration. Since it's not configurable via an environment variable, it should be removed from the variables section.