sandbox-agent

Data Exfiltration

Supply Chain Compromise

Malicious tool definition detected

Disable it with: ```bash sandbox-agent server --no-telemetry ```

Shadow Persistence

Supply Chain Compromise

Supply Chain Compromise

Risky tool definition detected

For `.env.development` and `.env.development.local`, store `GITHUB_APP_PRIVATE_KEY` as a quoted single-line value with ` ` escapes instead of raw multi-line PEM text.

Data Exfiltration

Supply Chain Compromise

Data Exfiltration

Supply Chain Compromise

Malicious tool definition detected

**Upgrade to Tier 3+** for full network access 2. **Contact Daytona support** to whitelist `api.anthropic.com` and `api.openai.com` for your organization The `networkAllowList` parameter only works on Tier 3+: ```typescript await daytona.create({ snapshot: "my-snapshot", envVars: { ANTHROPIC_API_KEY: "..." }, networkAllowList: "api.anthropic.com,api.openai.com", // Tier 3+ only }); ``` See [Daytona Network Limits documentation](https://www.daytona.io/docs/en/network-limits/) for details.

Supply Chain Compromise

Data Exfiltration

Malicious tool definition detected

- OpenCode CLI (`opencode attach`) - OpenCode web UI - OpenCode TypeScript SDK (`@opencode-ai/sdk`) ## Quick start ### OpenCode CLI / TUI ```bash sandbox-agent opencode --port 2468 --no-token ``` Or start server + attach manually: ```bash sandbox-agent server --no-token --host 127.0.0.1 --port 2468 opencode attach http://localhost:2468/opencode ``` With authentication enabled: ```bash sandbox-agent server --token "$SANDBOX_TOKEN" --host 127.0.0.1 --port 2468 opencode attach http://localhost:2468

Tool passed security scan

Malicious tool definition detected

Risky tool definition detected

```bash cURL curl -X PUT "http://127.0.0.1:2468/v1/fs/file?path=./uploads/data.csv" \ --data-binary @./data.csv ``` The upload response returns the absolute path.

Supply Chain Compromise

Supply Chain Compromise

Malicious tool definition detected

Data Exfiltration

Shadow Persistence

Supply Chain Compromise

Supply Chain Compromise

Privilege Escalation

Destructive Action

Resource Abuse

Shadow Persistence

Malicious tool definition detected

Malicious tool definition detected

To add it to an agent using the Skills CLI: #### npx ```bash npx skills add rivet-dev/skills -s sandbox-agent ``` #### bunx ```bash bunx skills add rivet-dev/skills -s sandbox-agent ``` If you run a reverse proxy in front of the docs, make sure `/skill.md` and `/.well-known/skills/*` are forwarded to Mintlify.

Malicious tool definition detected

This extra hop is recommended because it keeps auth/token logic on the backend and makes persistence simpler.

Supply Chain Compromise

Malicious tool definition detected

The sandbox-agent converts these into a universal event schema, giving you a consistent session transcript regardless of which agent you use. The schema is defined in [OpenAPI format](https://github.com/rivet-dev/sandbox-agent/blob/main/docs/openapi.json). See the [HTTP API Reference](/api-reference) for endpoint documentation.

Malicious tool definition detected

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan