Security audit
Security checks for vulnerabilities and agentic risk
Pi-hole operations are clearly scoped, but setup can run unverified downloaded code and introduce additional agent skills without clearly explaining those changes.
Review and approve the CLI installation separately before use; its downloaded installers could not be inspected here. Additional agent skills may be installed automatically. The [CLI command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables) documents OO_SKILLS_SYNC_DISABLED=1 to disable startup skill synchronization. Consider whether you trust OOMOL with access to Pi-hole credentials and DNS activity, and retain the required confirmations for changes.
The supplied command executes a third-party installation script rather than managing Pi-hole. Nothing in the provided chunk establishes this installer as a supporting dependency for Pi-hole functionality. The downloaded script's further behavior cannot be determined from the supplied code.
The supplied code only invokes a login command and shows no Pi-hole interaction. Authentication could be a supporting implementation detail if oo were established as a Pi-hole client, but the supplied content provides no such connection. No credential theft or other additional behavior can be inferred from this command alone.
The fallback setup instructs the agent to execute a mutable remote script directly with Bash, without pinning its version or verifying its integrity; the PowerShell alternative has the same weakness. Compromise of the installer endpoint or release pipeline could execute attacker-controlled code with the invoking user's privileges and access local secrets or alter the system. Its restriction to missing-CLI errors and its legitimate dependency purpose reduce exposure but do not establish the downloaded code's integrity.
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
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