Security audit
Security checks for vulnerabilities and agentic risk
Builder.io changes require confirmation, but setup directs the agent to execute unverified remote code without a separate approval step.
Review the setup behavior before installing. Prefer a separately approved, verified CLI installation and review or disable its automatic agent-skill synchronization using the publisher's documented controls. OOMOL will mediate Builder.io access, so connect only the intended account and permissions. Keep the existing confirmations for content changes and deletion. The remote installers and hosted connector implementation remain unverified; no malicious behavior was established.
The supplied command targets an Oomol installer, not Builder.io resources, and executes the downloaded script locally. Nothing in the supplied chunk establishes this installation as a supporting requirement for Builder.io. The remote script's further behavior cannot be determined from this chunk.
The command executes a remotely downloaded, mutable script directly in Bash without a pinned version, integrity verification, or inspection; the PowerShell alternative uses the same download-and-execute approach. Compromise of the installer distribution could therefore execute attacker-controlled code with the invoking account's privileges, exposing local data and credentials; legitimate dependency setup and HTTPS do not eliminate this supply-chain risk.
oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux
The missing-command fallback instructs installation without requiring disclosure or approval for executing an installer and changing the local environment. Although conditional and related to a legitimate dependency, permission to operate on Builder.io data does not necessarily authorize installing software; the write-confirmation rules cover Builder.io state, not local installation.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.
- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.
## Resources