# Scan: AISLE platform > GAMMA-Ray v0.0.155 (beta, for review; every rating is experimental). An example GAMMA-Ray beta rating of AISLE platform: freedom 1, 4, 1 across its configurations; deployment governance not assessed. > Page: https://gamma-ray.sgit.ai/scans/aisle-platform/ · Source: data/scans/aisle-platform.json Example · beta rating · a product as its vendor documents it · read 2026-11-10 · not seen by the vendor AISLE's platform of AI agents that finds vulnerabilities in source code, triages them, writes and tests patches, and delivers them as pull requests for people to merge. A scan of a product as its vendor documents it, not of any one deployment. Made by the report studio: a researcher-assessor, a challenger, then the scorer. Built only from AISLE's own public product, blog and about pages, and third-party vulnerability records (OpenSSL, curl, Samba) that credit its work. 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.* 1 Freedom as shipped Answers 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 platform connected to a customer's repositories, delivering findings and patches as pull requests. | 1 Answers | 9 | nothing | | **Fixes as pull requests** | The customer sets, per severity and repository, that AISLE goes on from triage to open a pull request with a tested patch. | 4 Acts widely | 9 | the agent works independently; the person approves critical decisions only | | **With the MCP server** | A customer connects AISLE's read-only MCP server to its own coding agent. | 1 Answers | 9 | it exposes an agent interface: a published mcp server, an agent card, or an api documented for agents to call | 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. ## Seen, and not credited - OpenSSL advisories credit vulnerabilities to researchers of Aisle Research. The credits name people, so they show AISLE's team at work, not the agent acting on its own. [Source](https://openssl-library.org/news/vulnerabilities/index.html) - The open-source page shows an 'aisle-security' bot account inside a styled mock-up of a GitHub thread. A mock-up graphic, not a statement that the account exists; I26 rests on the OpenSSL story alone. [Source](https://aisle.com/open-source) ## 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. The remediation FAQ states AISLE builds the repository in an isolated container, applies its patch and runs the tests. [Source](https://aisle.com/platform/autonomous-remediation) (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. The page states AISLE writes a patch, runs it against the customer's tests and opens a pull request. [Source](https://aisle.com/platform/autonomous-remediation) (documented) - **As shipped.** It is in production: a public source names a customer or gives usage figures for what it does on its own. A customer story names Productboard, which rolled AISLE out across all 56 repositories and integrated its AI-powered pull requests into its workflow; the named customer is what is counted, as the page publishes no count of pull requests or tasks. CVE credits to Aisle Research name staff researchers and are not counted here. [Source](https://aisle.com/customers/productboard) (documented) ### How far does it reach? - *Not evidenced.* It works in one domain's data. - **As shipped.** It works across several domains or systems. The platform page states it plugs into the customer's scanners, repositories and CI. [Source](https://aisle.com/platform) (documented) - **As shipped.** It connects to external tools or services across a trust boundary. AISLE connects from its own service to the customer's hosted version control systems. [Source](https://aisle.com/platform/vulnerability-discovery) (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. - *Not evidenced.* Others build on it: third parties publish integrations, skills or agents for it. - **Available, if the operator turns it on.** It exposes an agent interface: a published MCP server, an agent card, or an API documented for agents to call. AISLE's announcement post, published 9 November 2026, states its MCP server gives a customer's coding agent, such as Claude Code, OpenAI Codex or Cursor, read-only access to AISLE findings through five tools, with sign-in by OAuth or a personal access token. [Source](https://aisle.com/blog/announcing-the-aisle-mcp-server) (documented) ### 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. - **Available, if the operator turns it on.** The agent works independently; the person approves critical decisions only. The page states AISLE writes and tests a patch and opens a pull request, that the customer decides per severity and repository how far it goes, and that a person on the customer's team merges; no default is stated. [Source](https://aisle.com/platform/autonomous-remediation) (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 home page states what the system is for: finding, fixing and verifying vulnerabilities in source code. [Source](https://aisle.com/) (documented) - **As shipped.** Its autonomy limits and the tools it may use are defined. The customer sets how far AISLE acts on its own, per severity and per repository. [Source](https://aisle.com/platform/autonomous-remediation) (documented) - **As shipped.** Its limits and known failure cases are documented for those who use it. The page states which findings get guidance instead of a patch, and that a fix breaking tests goes back to the team. [Source](https://aisle.com/platform/autonomous-remediation) (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. - *Not evidenced.* It asks for narrower access than the whole account. - **In this deployment.** It has its own identity, separate from any person's. AISLE's OpenSSL story states maintainers invoke it by tagging the GitHub handle @aisle-analyzer. Stated by AISLE; the account was not checked on GitHub. [Source](https://aisle.com/customers/openssl) (documented) - *Not evidenced.* Its identity is cryptographic and can be checked by others. - *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. A merge to the main branch needs a person on the customer's team; AISLE opens the pull request and waits. [Source](https://aisle.com/platform/autonomous-remediation) (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. The enterprise FAQ states every finding and fix is logged through to the approved pull request, with timestamps and approvers; documented only, not observed. [Source](https://aisle.com/enterprise) (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? - *Not evidenced.* A limit on it is enforced by something outside its own reach. - *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? - *Not evidenced.* It tells the people it talks to that it is an AI. - **As shipped.** There is a channel to report problems with it or contest its output. Users can contest a triage decision by explaining why and sending the issue back for re-assessment. [Source](https://aisle.com/platform/vulnerability-triage) (documented) - *Not evidenced.* It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent card. ### What data does it use, and under what rules? - **As shipped.** The data it uses is described. The privacy policy lists customer data as code repositories and related data submitted to the service. [Source](https://aisle.com/privacy-policy) (documented) - *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. - **As shipped.** Its value is measured. The enterprise page states a figure for engineering hours saved, and the remediation page gives monthly patch and hours figures; no method is published. [Source](https://aisle.com/enterprise) (documented) - **As shipped.** It is improved on a regular cycle. The deployment comparison states updates and intel are continuous for Managed SaaS and delivered monthly for private cloud and on-prem; this is an update cadence, with no improvement process described. [Source](https://aisle.com/deployment/managed-saas) (documented) - *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 (`z11yqwik`, published 2026-11-10). Anyone can read it with this key: `sgit_public_read_5dcfc650a15adce6282cb5996d1cd2f57f8bd817588886e419e57a94246fdabd:z11yqwik` With [sgit](https://sgit.ai/): `sgit clone sgit_public_read_5dcfc650a15adce6282cb5996d1cd2f57f8bd817588886e419e57a94246fdabd:z11yqwik`. The key reads; it cannot write. An operator who wants to add what only they hold forks the vault into a private one.