Security audit
Security checks for vulnerabilities and agentic risk
The Typebot reading functions fit the stated purpose, but setup can execute unverified installers and introduce broader agent changes without clear user control.
Review and install a specific CLI release yourself before enabling this skill, and decide whether OOMOL should handle your Typebot credentials and results. Require approval for dependency installation. To prevent the documented startup skill synchronization, set OO_SKILLS_SYNC_DISABLED=1 before CLI use; see [publisher controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The bundled skill was fully inspected, but the remote installers and deployed connector implementation remain unverified.
The supplied chunk performs remote script execution rather than searching or reading Typebot data. It accesses an Oomol installation endpoint, and nothing in the supplied code establishes that this installation is a supporting implementation detail required for the declared Typebot functionality. The downloaded script's contents and any further effects are not available for assessment.
The command executes a remotely supplied script immediately, without version pinning, signature verification, or an opportunity to inspect it; the PowerShell alternative has the same issue. Compromise of the distribution endpoint or release pipeline could execute attacker-controlled code with the agent's local permissions, exposing files and credentials even though this is a legitimate dependency-installation context.
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
On a missing-command error, the skill directs the agent to install software without first disclosing local changes or obtaining installation approval. A request to read Typebot data does not necessarily authorize modifying the local environment, although the missing-dependency condition limits when this behavior occurs.
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