Security audit
Security checks for vulnerabilities and agentic risk
The market-data features fit the stated purpose, but setup can execute changing remote code and introduce additional agent skills without clearly explaining those effects.
Review the CLI setup before enabling this skill. Prefer a verified CLI release and explicitly decide whether to allow additional agent skills. Upstream documents OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization in its [environment settings](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). OOMOL handles the connected service credentials and may charge for requests. The complete bundled artifact was inspected; remote installer contents, the deployed CLI version, and server-side connector behavior remain unverified.
The supplied command installs software by executing externally hosted shell code; it does not search or read Token Metrics data. Nothing in the supplied content establishes this installer as a supporting dependency for the declared purpose. The remote script's contents and any further effects are unknown.
The supplied chunk contains only a login command, with no Token Metrics reference or data-access operation. Authentication could support a data skill, but the provided code does not establish that connection and implements a materially different primary operation.
Piping a mutable remote installer directly into bash executes its contents without inspection or verification against a trusted release. HTTPS reduces transport interception risk but does not protect against a compromised distribution server or malicious installer update; this is the same underlying installation risk identified by SQP-2.
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 instructions direct execution of remotely downloaded shell and PowerShell scripts without review, integrity verification, or explicit approval for installing executable software. Although installation is a legitimate dependency and only triggered when the CLI is missing, compromised installer delivery could execute arbitrary code with the agent's local permissions.
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