> AI agents: this is one page from PostHog's docs. Full index of Markdown docs for LLMs: https://posthog.com/llms.txt

# Cloud Tasks security

Canonical URL: https://posthog.com/docs/tasks/security

Cloud Tasks run agents in isolated cloud sandboxes. This page describes their access to code, snapshot storage, and network controls.

Last reviewed: October 27, 2026.

## Code access and storage

Repository cloning is optional. When a task needs code access, it can clone the selected repository into its sandbox. Agents can send relevant code and product data to large language model (LLM) providers during a run.

Sandbox lifetime and saved snapshots have separate limits:

| Data or environment | Retention |
| --- | --- |
| Running sandbox | Each sandbox has a maximum lifetime of 6 hours. PostHog terminates it when the run ends. |
| Repository snapshots from interactive cloud runs | Some tasks save snapshots for resume. These snapshots have no automatic expiry and remain stored indefinitely. |

Snapshot creation depends on the task and its execution mode. A snapshot preserves files so an interactive run can resume after its sandbox stops. The 6-hour sandbox limit does not delete a saved snapshot.

[Self-Driving agents](https://posthog.com/docs/self-driving/security.md) do not create repository snapshots.

Reports, conversations, execution records, and output files are separate records. Code that an agent includes in a report or model request is subject to the retention for that record or provider.

Review [AI data processing access](https://posthog.com/docs/posthog-ai/allow-access.md) before you enable agents for your organization. See [data storage](https://posthog.com/docs/privacy/data-storage.md) for general PostHog storage and deletion information.

## Execution controls

Cloud Tasks use isolated sandboxes and shell execution policies. Network access depends on the task environment. A restricted environment allows approved destinations. An environment with full network access permits unrestricted outbound connections.

See [sandbox network access](https://posthog.com/handbook/engineering/ai/sandboxed-agents.md#network-access) for the available settings. For the additional safety checks used by Self-Driving agents, see [Self-Driving security](https://posthog.com/docs/self-driving/security.md).