Security audit
Security checks for vulnerabilities and agentic risk
The Fivetran reads are appropriate, but setup can execute unverified downloaded code, and the required CLI has undisclosed effects on other agents’ skills.
Review setup before use. Install a verified CLI release yourself and check the permissions granted through OOMOL. The provider documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization. The remote installer and hosted connector implementation remain unverified; no malicious behavior was established.
The supplied command performs remote script execution rather than searching or reading Fivetran data. Nothing in the chunk establishes that installing the Oomol CLI supports the declared Fivetran functionality. The script's contents are not supplied, so its further effects cannot be determined.
Piping an HTTPS response directly into Bash executes mutable remote code without independent integrity verification or an opportunity to inspect it first. Compromise of the installer host or publishing pipeline could therefore lead to arbitrary code execution with the invoking user's permissions. The domain is consistent with the documented CLI provider, so this is a supply-chain exposure rather than evidence of a malicious destination; the PowerShell alternative has the same underlying 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 fallback instructs the agent to execute downloaded shell or PowerShell scripts without requiring explicit installation approval or verification of the downloaded code. Such scripts execute with the invoking user's privileges and could compromise local files or credentials if the distribution source is compromised. Restricting installation to a missing-CLI error reduces exposure, but does not make system-changing installation implicitly authorized by a Fivetran read request.
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