Security audit
Security checks for vulnerabilities and agentic risk
Starton operations have clear approval rules, but setup executes unverified remote code and leaves broader agent-skill changes undisclosed.
Review the CLI setup before enabling this skill. Prefer a separately verified, pinned installation. Current publisher documentation provides OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization; configure it before invoking oo if you want to avoid additional agent-skill changes. Connect only the intended Starton account, consider OOMOL's intermediary access, and retain the required write/delete confirmations. The remote installer and connector implementation remain outside the inspected package.
The supplied command contains no Starton operations and instead executes an installer from cli.oomol.com. No connection is established between this installer and the declared Starton functionality, making it a materially different capability rather than an evident supporting implementation detail. The downloaded script's contents and further effects cannot be determined from this chunk.
The supplied code only initiates CLI login and contains no Starton-specific operations or configuration linking that login to Starton. Authentication could support the declared purpose, but the provided chunk shows only authentication as its behavior, not a Starton integration.
Piping a mutable remote script directly into Bash executes its contents without prior integrity or authenticity verification beyond HTTPS. A compromised distribution endpoint could therefore execute arbitrary code with the agent's permissions; this is the same underlying installation risk identified by SQP-2, not an independent attack path.
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 fallback setup directs execution of downloaded shell or PowerShell code without an explicit installation approval gate or artifact verification. If an agent executes it and the installer source is compromised, the code runs with the agent's local privileges and could access files or credentials; the missing-CLI condition limits exposure but does not remove the 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