Security audit
Security checks for vulnerabilities and agentic risk
Radar lookups are appropriately scoped, but automatic setup runs unverified downloaded code and leaves broader changes to your agent environment unclear.
Review and install a verified CLI release separately before allowing setup commands to run. Decide whether additional agent skills are acceptable; the publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill writes. Your Radar queries pass through OOMOL using your connected account. The installer contents remain unverified, but no malicious payload was established. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables)
The supplied command performs remote script execution, not a Radar query or data read. Nothing in the chunk establishes that this installer is a supporting dependency for Radar. The downloaded script is not provided, so its further behavior and any system changes cannot be determined.
The curl-to-bash command executes the installation endpoint's current response without checking its contents or authenticity beyond HTTPS transport. A compromised endpoint could therefore run attacker-controlled code with the invoking user's permissions; this is the same underlying installer risk as SQP-2, not evidence that the endpoint is currently malicious.
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
Both setup examples immediately execute remotely downloaded scripts without content review, version pinning, or independent integrity verification. If the installation endpoint or delivery infrastructure is compromised, the script could execute arbitrary code with the invoking user's permissions; conditional first-time setup reduces exposure but does not remove this risk.
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