Security audit
Security checks for vulnerabilities and agentic risk
The messaging workflow has approval controls, but setup directs the agent to execute unverified online installers without a separate approval step.
Review and approve the CLI installation separately before allowing setup. Confirm whether its documented agent-skill synchronization is acceptable; the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents a synchronization-disable setting. Connect only the intended Wire2Air account and review recipients, message content, and costs before sending. Remote installer contents and the exact installed runtime were not verified.
The supplied code executes an Oomol-hosted installer rather than interacting with Wire2Air. Dependency installation can be a supporting implementation detail, but the chunk provides no evidence that this installer is related to or required for Wire2Air functionality. The downloaded script's contents and resulting system changes cannot be determined from this chunk.
Piping a live HTTPS response directly into bash executes mutable remote code with the invoking user's privileges, without a pinned version or independent integrity verification. Compromise of the installer distribution path could expose locally accessible files and credentials or alter the system; the related OOMOL domain and conditional setup make this plausible dependency management rather than evidence of malicious intent.
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 an agent to execute remote shell or PowerShell installers without first explaining the local code execution and obtaining installation approval. Restricting setup to a missing CLI reduces exposure, but a request to operate Wire2Air does not necessarily authorize installing software or making other local system changes.
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