Security audit
Security checks for vulnerabilities and agentic risk
The speech workflow is reasonable, but its required tool can persistently add skills to other agent tools without this skill explaining that behavior.
Review the CLI's installation and cross-agent skill changes before proceeding. Prefer a verified release and disable startup skill syncing with OO_SKILLS_SYNC_DISABLED=1 if those changes are unwanted, as described in the [CLI reference](https://raw.githubusercontent.com/oomol-lab/oo-cli/main/docs/commands.md). Approve speech payloads knowing they pass through OOMOL to Doubao Speech. The sole bundled file was inspected; remote installer contents and hosted connector behavior remain unverified.
The supplied code performs remote script execution rather than any visible Doubao Speech operation. Dependency installation could be a supporting implementation detail, but this chunk provides no evidence that the installer supports the declared purpose. The downloaded script's contents and any further effects cannot be determined from the supplied code.
The setup instructions pipe a remotely fetched, unpinned script directly into Bash, and the PowerShell alternative uses the same fetch-and-execute pattern. If the distribution endpoint or release infrastructure is compromised, following these instructions could execute attacker-controlled code with the invoking user's permissions; the missing-CLI prerequisite limits exposure but 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 workflow instructs the agent to send action payloads through the connector, including inputs for speech-recognition and text-to-speech tasks. Although the file identifies the services and requires confirmation for writes, it does not warn that submitted text or recording inputs are shared with third-party services.
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