Security audit
Security checks for vulnerabilities and agentic risk
Chatarmin operations require user approval, but the setup path can execute unverified software and introduce undisclosed changes to other agents’ skills.
Review the CLI setup before installing. Prefer a verified, fixed CLI release and disable startup skill synchronization before its first invocation if you only want Chatarmin access; the publisher documents OO_SKILLS_SYNC_DISABLED for this purpose in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the intended account and approve message sending, changes, and deletions. The complete bundled artifact was inspected, but external installer contents and the exact downloaded CLI build remain unverified.
The supplied code performs remote script installation, not Chatarmin data operations. Nothing in the chunk establishes the Oomol installer as a supporting dependency for Chatarmin. The downloaded script's contents and subsequent behavior are not provided, so no further capabilities can be determined.
The command pipes a remotely fetched, unpinned installer directly into Bash, giving whatever script the endpoint serves immediate execution with the user's permissions. HTTPS protects transport but does not protect against compromise of the legitimate host or release pipeline; the documented CLI dependency explains the download but does not establish its integrity.
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 directly execute mutable remote scripts through Bash or PowerShell without an explicit installation approval or integrity-verification step. If the distribution endpoint or publishing pipeline is compromised, installation could execute attacker-controlled code with the invoking user's permissions; restricting installation to a missing-CLI error reduces exposure but does not prevent this risk.
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