Security audit
Security checks for vulnerabilities and agentic risk
The Speechmatics integration is clearly described, but setup permits downloaded code execution and does not disclose the CLI’s broader changes to agent skills.
Review setup before enabling this skill. Install a verified CLI release yourself and decide whether to allow its additional agent skills; upstream documents OO_SKILLS_SYNC_DISABLED=1 to disable startup skill synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). OOMOL mediates your connected Speechmatics account and requests. The exact remote installers remain unverified; the reviewed artifact does not establish theft, deception, or destructive behavior.
The supplied code installs software from Oomol and shows no Speechmatics interaction or evidence that this installation supports the declared functionality. This is an undeclared capability and uses an inconsistent resource. The remote script's contents are not supplied, so its specific installation actions and side effects cannot be determined.
Piping a mutable HTTPS response directly into bash executes remote code without first verifying its contents or provenance beyond transport security. Compromise of the installer publisher or hosting infrastructure could expose local files and credentials or establish persistence under the executing account; the legitimate dependency context does not remove this supply-chain 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 setup instructions direct the agent to execute downloaded shell or PowerShell code without requiring user approval or integrity verification. A compromised installer or distribution endpoint could execute arbitrary code with the agent's local permissions; limiting installation to a missing-CLI error reduces frequency but does not mitigate that exposure.
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