Security audit
Security checks for vulnerabilities and agentic risk
The Wise features fit their purpose, but setup can execute unverified downloaded code and install additional agent skills without clear approval.
Review the setup behavior before installing. Prefer a separately approved, verified CLI installation, and disable automatic skill synchronization if you want changes limited to this Wise integration. Understand that OOMOL mediates access to your connected Wise account. The installer and hosted connector were not verified; the artifacts do not establish malicious intent.
The supplied command does not search or read Wise data; it executes an external installer. Nothing in the supplied chunk establishes that this installation supports the declared Wise functionality. The downloaded script's contents are not provided, so its further effects cannot be determined.
Authentication could support a Wise integration, but the supplied chunk contains only a login command, with no Wise-specific operation or demonstrated connection to Wise. As supplied, its primary behavior differs materially from the declared data-access purpose.
Piping a mutable remote script directly into Bash executes its contents without independently verifying the artifact's integrity or reviewing it first. HTTPS protects transport but does not prevent a compromised distribution endpoint from serving malicious code capable of accessing local files and credentials; the PowerShell installation example has the same underlying 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 setup fallback directs the agent to execute downloaded installer code without an explicit approval step for local system changes. A request to read Wise data does not inherently authorize software installation, and a compromised installer could execute with the invoking user's permissions; the missing-CLI condition limits when this exposure occurs.
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