# Scan: GitHub Copilot cloud agent > GAMMA-Ray v0.0.3 (beta, for review; every rating is experimental). An example GAMMA-Ray beta rating of GitHub Copilot cloud agent: freedom 4, 4 across its configurations; deployment governance not assessed. > Page: https://gamma-ray.sgit.ai/scans/github-copilot-cloud-agent/ · Source: data/scans/github-copilot-cloud-agent.json Example · beta rating · a product as its vendor documents it · read 2026-11-10 · not seen by the vendor The asynchronous agent on GitHub.com that creates branches, writes code and opens pull requests in response to assigned issues. An example scan of a product as its vendor documents it, not of any one deployment. Built only from the vendor’s own documentation. Nothing was tested. If you are the vendor and something here is wrong, the correction will be made and dated. *Figure. The label for this rating; its contents are in the text.* 4 Freedom as shipped Acts widely 4 Freedom at most Acts widely 9 Controls it brings as shipped n/a Deployment governance not assessed ## How to read it This is a product, not a deployment. A product has no owner, no policy in force and no mandate until somebody runs it, so it is given **no governance level and no level held**: those belong to a deployment. What a product has is a freedom level for each way it can be configured, and a list of the controls each configuration brings. *Figure. The freedom level of each configuration; the table has the same.* | Configuration | What changes | Freedom | Controls | Turned on by the operator | |---|---|---|---|---| | **As shipped** | The firewall and its recommended allowlist are on. | 4 Acts widely | 9 | nothing | | **With external tools connected** | Model Context Protocol servers and other applications. | 4 Acts widely | 9 | it connects to external tools or services across a trust boundary | The same product is a different agent in each row. A rating of a deployment starts by saying which row it is. An indicator with no evidence is reported as not evidenced; it is never read as a no. ## The profile *Figure. One square per indicator, by question; every answer is listed below.* ## The grant: what it can actually do The questions measure what is said about an agent: its purpose, its rules, its controls. The grant is the other half: what its permissions let it do, capability by capability, and what stands in the way of each. This is RiskMandate's measurement, and it depends on the permissions a deployment was given. **Not measured.** Not measured. No deployment shape for this product is published in the capability grammar; the closest published shape, a hosted Actions runner with no agent, is not the same thing. ## Seen, and not credited - New code is analysed with CodeQL, secret scanning and dependency analysis during generation. That tests what the agent produces. No indicator asks for it yet, and it is not evidence that the agent itself is tested. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) ## What its evidence reaches *Figure. The mashup graph with this agent's evidenced indicators lit.* ## Every answer, with its source ### What is the agent built on? - *Not evidenced.* It is a vendor's assistant, used as supplied. - *Not evidenced.* It runs on an AI platform with the organisation's own data, without executing arbitrary code. - *Not evidenced.* It is configured on a low-code or no-code builder and acts on real organisational data. - **As shipped.** It generates and executes code with local or cloud privileges. It writes code in an "ephemeral, firewalled environment". [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - *Not evidenced.* It is built in-house: the organisation controls its identity, tools and boundaries. ### Does it act, or only answer and recommend? - *Not evidenced.* It follows fixed rules, with no reasoning. - *Not evidenced.* It retrieves information and recommends actions; a person acts. - **As shipped.** It executes actions itself. It "can create branches, write code, and open pull requests in response to assigned issues". [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) ### How far does it reach? - *Not evidenced.* It works in one domain's data. - **As shipped.** It works across several domains or systems. Repositories, issues and pull requests across one organisation. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - **Available, if the operator turns it on.** It connects to external tools or services across a trust boundary. It "can receive information and context from MCP" and from external applications. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) ### Does it work with other agents? - *Not evidenced.* Several agents coordinate inside the organisation. - *Not evidenced.* Agents operate across organisational boundaries or disparate stacks. - *Not evidenced.* There is a published protocol or communication layer between agents. ### What is the person's role? - *Not evidenced.* The person operates: every action is prompted and controlled by them. - *Not evidenced.* The agent suggests; the person reviews and approves each action. - *Not evidenced.* The agent handles routine tasks; the person is consulted on exceptions. - **As shipped.** The agent works independently; the person approves critical decisions only. The person assigns a task and reviews the pull request before merging. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - *Not evidenced.* The agent has full autonomy within boundaries; the person monitors. ### Is what it is for written down? - **As shipped.** Its purpose and permitted tasks are stated in writing. The vendor states intended uses: maintenance, feature development, prototyping. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - **As shipped.** Its autonomy limits and the tools it may use are defined. "It can only push to a single branch"; it has no access to Actions secrets beyond those configured for it. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - **As shipped.** Its limits and known failure cases are documented for those who use it. The page lists limitations: limited scope, inaccurate code, security risks, public code matches. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) ### Does it have its own identity and only the access it needs? - *Not evidenced.* What it can reach is enumerated: scopes, permissions, tools. - *Not evidenced.* Its authorisation is published as metadata that anyone can read. - **As shipped.** It asks for narrower access than the whole account. Read-only where the user has only read access; one branch to push to. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - *Not evidenced.* It has its own identity, separate from any person's. - **As shipped.** Its identity is cryptographic and can be checked by others. Its commits are signed and show as Verified. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - *Not evidenced.* Its tokens are bound to the service they were issued for and are not passed on. ### Is it in a registry, with an owner? - *Not evidenced.* The organisation keeps a registry of its agents. - *Not evidenced.* Each agent has a named owner. - *Not evidenced.* Agents are retired by a defined process. ### Who is accountable for it? - *Not evidenced.* A named executive or body is accountable for the organisation's agents. - *Not evidenced.* Roles and responsibilities for AI risk are documented. ### Is there a policy that governs it? - *Not evidenced.* A governance policy for agents is published. - *Not evidenced.* Agents and use cases are classed by risk. - *Not evidenced.* The laws that apply to it are identified. - *Not evidenced.* New agents pass an approval or review before they run. ### Can a person step in or stop it? - **As shipped.** High-impact actions need a person's approval. Workflows triggered by its pull requests "require approval from a user with write access before they will run". [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - *Not evidenced.* There is a way to pause or stop it. - *Not evidenced.* There is a defined escalation path. ### Is what it does logged? - **Claimed, not counted.** Its actions are logged. Commits are authored by Copilot with the person as co-author; matches are shown in the agent session logs. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented; this fact has to be observed or measured to count) - *Not evidenced.* The log is tamper-evident and kept for a stated time. ### Is it watched while it runs? - *Not evidenced.* It is monitored in operation. - *Not evidenced.* Anomalies are detected in real time and raise alerts. ### What stands between it and what it should not do? - **Claimed, not counted.** A limit on it is enforced by something outside its own reach. "By default, Copilot’s access to the internet is limited by a firewall." The vendor adds that it "should not be considered a comprehensive security solution". [Source](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/coding-agent/customize-the-agent-firewall) (documented; this fact has to be observed or measured to count) - *Not evidenced.* A limit on it is a setting that its own account could change. - *Not evidenced.* A limit on it is a rule in prose. - *Not evidenced.* Policy is enforced as machine-readable rules. - *Not evidenced.* The difference between what it can reach and what it is for is stated. ### Is it tested, and are the results shown? - *Not evidenced.* Test or evaluation results are published. - *Not evidenced.* It is tested for safety and security, including by attack. - *Not evidenced.* People who did not build it take part in assessing it. ### What happens when it goes wrong? - *Not evidenced.* There is an incident process for agents. - *Not evidenced.* Incidents and errors are communicated to those affected. - *Not evidenced.* There is a plan for a failure of a third party it depends on. ### Do people know it is an AI, and can they answer back? - **As shipped.** It tells the people it talks to that it is an AI. Its commits and pull requests are attributed to Copilot. [Source](https://docs.github.com/en/copilot/responsible-use/copilot-coding-agent) (documented) - *Not evidenced.* There is a channel to report problems with it or contest its output. ### What data does it use, and under what rules? - *Not evidenced.* The data it uses is described. - *Not evidenced.* There are data quality rules for what it reads. - *Not evidenced.* Its privacy risk has been examined. ### What does it depend on from others? - *Not evidenced.* The models and third-party components it uses are listed. - *Not evidenced.* Third-party components are monitored and have risk controls. ### Has anyone independent checked? - *Not evidenced.* A public certificate or audit report covers it. - *Not evidenced.* Compliance evidence is produced continuously, ready for a regulator. ### Is the organisation behind it ready? - *Not evidenced.* There is a stated strategy for agents. - *Not evidenced.* The people who work with it are trained. - *Not evidenced.* Its value is measured. - *Not evidenced.* It is improved on a regular cycle. - *Not evidenced.* The organisation's risk management covers agents. ## The vault This rating, its evidence list, its grant and the questions it was made against are kept in a public sgit vault (`q7vudzvh`, published 2026-11-10). Anyone can read it with this key: `sgit_public_read_5681b4b6d6b4524d74282e9e1339326d0663f6d878b790be49cd3b1de028a63e:q7vudzvh` With [sgit](https://sgit.ai/): `sgit clone sgit_public_read_5681b4b6d6b4524d74282e9e1339326d0663f6d878b790be49cd3b1de028a63e:q7vudzvh`. The key reads; it cannot write. An operator who wants to add what only they hold forks the vault into a private one.