Security & Network

Cloud agents run in isolated, sandboxed environments with strict network controls. This page details the security architecture, data handling policies, and compliance posture.

Sandboxing

Each cloud agent run executes inside a dedicated, ephemeral container with strict resource and access controls. No two agent runs share a container.

Container Isolation

  • Dedicated container: each run gets its own container with an isolated filesystem, process namespace, and network stack.
  • No persistence: the container and all its contents are destroyed when the run completes or times out.
  • Resource limits: CPU, memory, and disk are capped per container to prevent abuse. Defaults: 2 vCPU, 4 GB RAM, 10 GB disk.
  • No privilege escalation: containers run as a non-root user with no sudo access.
  • Read-only system: the base filesystem is read-only. Only the workspace directory and /tmp are writable.

Shell Restrictions

The bash tool inside cloud agents runs in a restricted shell environment.

AllowedBlocked
File operations (cat, ls, cp, mv, rm within workspace)Network tools (curl, wget, ssh, nc)
Git operations (read-only: log, diff, blame, show)Git push, git remote operations
Build tools (npm, bun, cargo, go, make)Package installation from registries (blocked by network)
Test runners (vitest, jest, pytest, go test)Docker, container management
Text processing (grep, sed, awk, jq)System administration (systemctl, mount)

Note

Build tools are available, but package installation commands will fail because outbound network access is blocked. Pre-install dependencies by committing a lock file and node_modules (or equivalent) to your repository, or use a custom Docker image.

Network Isolation

Cloud agent containers have no outbound internet access by default. This prevents data exfiltration and reduces the attack surface.

Network Policy

DirectionPolicyDetails
Outbound to internetBlockedNo HTTP, HTTPS, DNS, or raw socket access to external hosts.
Outbound to Creor APIAllowedAgent communicates with the Creor API for LLM inference and status reporting.
Outbound to Git providerAllowed (read-only)Clone and fetch operations for the configured repository.
InboundBlockedNo inbound connections accepted. Container is not addressable.
Inter-containerBlockedNo container-to-container communication.

Custom Network Rules (Enterprise)

Enterprise plan customers can configure custom network allow lists to permit access to specific internal endpoints (e.g., private package registries or internal APIs).

1
2
3
4
5
6
7
8
# Enterprise network allow list (configured via dashboard)
{
"networkAllowList": [
"registry.internal.acme.com:443",
"api.internal.acme.com:443",
"npm.pkg.github.com:443"
]
}

Data Handling

Creor takes a minimal-data approach to cloud agent execution. Here is what happens to your code at each stage.

During Execution

  • Repository is cloned into the ephemeral container. The clone exists only in memory and on the container's temporary disk.
  • Code chunks are sent to the LLM provider for inference. These are processed in real time and not stored by Creor.
  • Tool call inputs and outputs are logged for the duration of the run to support status reporting and artifact collection.

After Execution

  • Container and all file contents are destroyed immediately.
  • Agent run metadata (status, timing, token counts) is retained for 90 days for billing and analytics.
  • Artifacts (diffs, reports) are stored encrypted and retained for 30 days or until you delete them.
  • Full conversation logs are retained for 7 days for debugging, then deleted.

What Creor Does Not Store

  • Full repository contents beyond the agent run.
  • Your API keys, secrets, or credentials found in the repository.
  • LLM conversation history beyond the 7-day debugging window.
  • File contents from files the agent read but did not include in artifacts.

Warning

While Creor does not intentionally store your code, the LLM provider processes code snippets during inference. Review your LLM provider's data handling policy. When using the Creor Gateway, inference data is not used for training.

Authentication & Access

Cloud agents authenticate using your workspace's API key and the Git provider integration you configured.

ComponentAuthenticationPermissions
Creor APIAPI key (Bearer token)Scoped to workspace. Cannot access other workspaces.
GitHubCreor GitHub App (OAuth)Repository access as configured. Read + write for PR comments.
GitLabPersonal access tokenScoped by token permissions.
BitbucketApp passwordScoped by app password permissions.
LLM providerWorkspace credentialsManaged by Creor. Agent does not see raw API keys.

API keys have configurable scopes. A key with "Cloud Agents" scope can only launch and manage agent runs -- it cannot access billing, team management, or other dashboard features.

Compliance

Creor's cloud infrastructure is designed to meet common compliance requirements.

StandardStatusDetails
SOC 2 Type IIIn progressAudit expected to complete Q3 2026.
GDPRCompliantEU data processing agreement available on request.
CCPACompliantCalifornia consumer privacy rights supported.
HIPAANot yetPlanned for enterprise tier. Contact sales for timeline.
Data residencyUS (default)EU data residency available for enterprise customers.

Note

For the latest compliance documentation and to request a DPA, contact security@creor.ai or visit the Trust Center at creor.ai/trust.

Security FAQ

Can a cloud agent access my other repositories?

No. Each agent run is scoped to a single repository. The clone credentials are limited to the specific repository and branch you specify.

Can a cloud agent push commits to my repository?

No. Cloud agents have read-only Git access. They produce artifacts (diffs, comments) that you apply manually. The Bugbot integration posts PR review comments using the GitHub API, but it cannot merge, push, or modify branch protection rules.

Is my code used to train AI models?

No. Code processed by cloud agents via the Creor Gateway is never used for model training. If you use a third-party LLM provider directly (BYOK), check that provider's data policy.

What happens if a cloud agent encounters a secret in my code?

The agent includes a secret scanner that detects API keys, passwords, and tokens in code. If a secret is found, it is redacted in the agent's output and flagged as a security issue. However, this is best-effort -- use a dedicated secrets manager and avoid committing secrets to your repository.