Security audit
Security checks for vulnerabilities and agentic risk
The ProjectManager reads are appropriately scoped, but setup can run an unverified installer whose broader effects on agent skills are not explained.
Review setup before installing. Prefer a verified, preinstalled CLI and explicitly approve any software installation. Check its automatic skill synchronization; the publisher documents OO_SKILLS_SYNC_DISABLED as a control in the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the ProjectManager permissions you need and understand OOMOL's credential handling and billing. Remote installer behavior remains unverified.
The supplied command performs remote script execution for an Oomol CLI installer rather than searching or reading ProjectManager data. Nothing in the supplied chunk establishes this installation as a supporting dependency for ProjectManager access. The downloaded script's contents and further effects are not visible.
Piping a mutable remote script directly into Bash executes its contents without prior inspection or independent integrity verification; the PowerShell alternative has the same weakness. If the installer distribution infrastructure is compromised, this can execute attacker-controlled code with the agent's local permissions, exposing accessible files and credentials. HTTPS and the legitimate CLI dependency reduce some concerns but do not eliminate 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 setup instructions direct the agent to execute remote installers when the CLI is missing, without explaining their local effects or requiring installation-specific approval. Although this is a legitimate dependency and a conditional fallback, it expands a data-reading task into local software installation with the agent's operating-system permissions.
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