Security audit
Security checks for vulnerabilities and agentic risk
The lookups fit the stated purpose, but setup executes unverified remote code and the linked CLI documents broader changes to installed agent skills.
Review and install a verified CLI version yourself before agent use. Consider disabling its documented startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1. Send only information authorized for each lookup and expect possible credit usage. The remote installers and hosted connector implementation were not inspected.
The declared purpose concerns Gender-API.com data access, but the supplied command executes an installation script hosted on cli.oomol.com. Nothing in the supplied chunk establishes that this installer supports the declared service. Remote installer execution is a materially different, undeclared capability; the script's downstream behavior cannot be determined from this chunk.
The supplied code only invokes a login command. It contains no Gender-API.com reference, search operation, or data-reading operation. Although authentication can support API access, nothing in this chunk connects the oo login to the declared service, so its observed purpose does not match the description.
The setup command downloads a mutable remote script and immediately executes it without a pinned version or independent integrity verification; the PowerShell alternative has the same weakness. Compromise of the installer delivery infrastructure could execute arbitrary commands with the invoking user's privileges, although the missing-CLI prerequisite limits when this path is reached.
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
Calling every untagged read safe to run directly conflates absence of state changes with absence of privacy risk. These lookups can transmit names, email addresses, and IP hints through OOMOL to Gender-API.com; an explicit user-requested lookup reduces concern, but the blanket rule does not guard against sending unrelated or sensitive contextual data.
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