Security audit
Security checks for vulnerabilities and agentic risk
The IP lookups fit the stated purpose, but automatic setup executes unverified remote code and may install additional persistent agent skills.
Review the dependency setup before enabling this skill. Install and verify the CLI yourself, and consider disabling its automatic skill synchronization before running it. Submitted IP addresses pass through OOMOL to IPLocate. The complete bundled artifact was inspected; remote installer contents and the deployed connector implementation remain outside verified coverage. No artifact-backed evidence of malicious intent was found.
The supplied command does not access IPLocate or perform any declared data operations. Instead, it executes an external installation script from cli.oomol.com. Nothing in the supplied chunk establishes that this installer is a supporting implementation detail for IPLocate. The fetched script's contents and further effects are not available for inspection.
Piping an HTTPS response directly into bash executes mutable remote code without a review or integrity-verification step. HTTPS protects transport but not against a compromised publisher or distribution endpoint; the conditional setup context limits exposure but does not remove the arbitrary-code-execution 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 workflow instructs the agent to execute connector actions with user-supplied payloads, including individual or batches of IP addresses. Although it identifies IPLocate and OOMOL, it does not warn that the queried addresses are transmitted to these external services, and labels read actions as safe to run directly.
The missing-CLI fallback directs the agent to execute downloaded shell or PowerShell scripts without an explicit approval boundary or integrity verification. Although this is a legitimate dependency setup path, a compromised installer could execute arbitrary code with the invoking user's privileges; this overlaps with the SC2 finding.
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