Security audit
Security checks for vulnerabilities and agentic risk
The Lodgify actions fit the stated purpose, but setup can execute unverified downloaded code and introduce broader agent changes without clear user control.
Review the setup behavior before installing. Install a verified CLI release yourself, explicitly control its agent-skill synchronization, and authorize only the intended Lodgify account. OOMOL is the disclosed intermediary for connector access. The complete bundled artifact was inspected, but the downloaded installers and remote connector implementation remain unverified. The concern is uncontrolled setup and persistent agent changes, not evidence of credential theft or malicious intent.
The supplied command performs remote-script execution rather than searching or reading Lodgify data. Nothing in the description or supplied code establishes this installer as a necessary supporting component for Lodgify access. The downloaded script is not supplied, so its further behavior cannot be determined.
The command streams a remotely fetched installer directly into Bash without pinning its contents or independently verifying integrity; the PowerShell alternative has the same issue. If the distribution endpoint or its supply chain is compromised, following this fallback could execute attacker-controlled code with the agent's local permissions, potentially exposing files and credentials. The vendor-related HTTPS URL and missing-CLI condition reduce exposure but do not eliminate this trust boundary.
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 fallback instructs the agent to install tooling after a missing-command error without first explaining the local execution and system changes or obtaining explicit approval. Although conditional and operationally relevant, this can turn a read-only Lodgify request into an unexpected software installation with the agent's local privileges.
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