Security audit
Security checks for vulnerabilities and agentic risk
The Flagsmith workflow is coherent, but its automatic setup runs unverified remote code without clearly controlling lasting changes to the host.
Review the setup before use. Install a reviewed CLI version yourself and disable unwanted automatic skill synchronization. Connect only the intended Flagsmith environment, understanding that OOMOL processes requests and holds connector credentials. Preserve the required confirmations for writes. The remote installer and server-side connector implementation were unavailable for inspection; the Review verdict concerns setup control and disclosure, without evidence of malicious intent.
The supplied command installs or runs remote Oomol tooling rather than reading or modifying Flagsmith data. Nothing in the supplied chunk establishes this as a supporting dependency for Flagsmith. The downloaded script is not provided, so its additional effects cannot be determined; the observable mismatch is the unrelated remote installation and execution.
The command pipes a mutable remote script directly into Bash without integrity verification or an opportunity to review the downloaded artifact; the PowerShell alternative has the same issue. Compromise of the installation endpoint or release infrastructure could execute attacker-controlled code with the invoking user's privileges, although the documented vendor endpoint and conditional setup provide no evidence of deliberate malicious intent.
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 directs the agent to install software when the CLI is missing, without requiring approval for local changes or explaining their scope. Approval to operate Flagsmith does not necessarily authorize running an installer on the host, although restricting this behavior to a missing-command error reduces its exposure.
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