Security audit
Security checks for vulnerabilities and agentic risk
Campaign actions have clear approval controls, but automatic setup can execute unverified software without separate approval.
Review and approve CLI installation separately before allowing setup. Prefer a verified release and consider disabling automatic skill synchronization using OO_SKILLS_SYNC_DISABLED=1 where supported. [Synchronization controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) Campaign content is processed through OOMOL and Campaign Cleaner; connect only the intended account and retain the required write and deletion confirmations. The remote installers and hosted implementation were not verified.
The supplied code performs a remote installer execution rather than any demonstrated Campaign Cleaner operation. Nothing in the supplied content establishes this installer as a supporting dependency for the declared purpose. The downloaded script is not provided, so its further behavior cannot be assessed.
The command executes a remotely retrieved script immediately, without pinning an artifact or verifying its integrity before execution. A compromised installer host or release pipeline could execute arbitrary code with the agent process's permissions; HTTPS and the legitimate setup context do not eliminate this supply-chain risk. The PowerShell example has the same weakness.
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
When the CLI is missing, the skill directs the agent to install software without first obtaining approval for changes to the local environment. The error-triggered fallback limits when this occurs, but authorization to manage campaigns does not automatically authorize local software installation; the write and destructive-action confirmations only cover Campaign Cleaner state.
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