Security audit
Security checks for vulnerabilities and agentic risk
The translation workflow is appropriate, but setup executes unverified remote code and can add other agent skills without explaining those changes.
Review and verify the CLI installation before allowing automatic setup. Its installer contents remain unverified. If additional agent skills are unwanted, the publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill writes; configure it before running oo. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) Submit only text you intend OOMOL and Lingvanex to process.
The supplied command performs remote script execution for an apparently unrelated CLI installation. It contains no Lingvanex API interaction, and nothing provided establishes this installation as a supporting dependency. The downloaded script's further behavior cannot be determined from this chunk.
The supplied code performs a login operation rather than the declared Lingvanex data-access functionality. Authentication could be a supporting implementation detail, but this chunk provides no evidence that the oo login supports Lingvanex or that the declared functionality is implemented.
The setup command pipes a remotely fetched, mutable script directly into Bash without integrity verification or an opportunity for inspection. Compromise of the installer distribution path could execute arbitrary code with the invoking user's privileges, exposing local files and credentials; conditional execution when the CLI is missing reduces exposure but does not remove the 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 submit action payloads through the OOMOL connector to Lingvanex, but does not warn that translation or language-detection inputs leave the user's environment. Labeling untagged actions as safe reads on line 46 overlooks this disclosure risk, even though those actions do not change provider 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