Security audit
Security checks for vulnerabilities and agentic risk
The Plasmic reads fit the stated purpose, but setup can execute downloaded code and introduce persistent agent changes without a clear approval step.
Review and approve CLI installation separately before allowing setup. Use an inspected, verified release and consider the publisher-documented OO_SKILLS_SYNC_DISABLED control to prevent automatic skill synchronization. Connect only the Plasmic account and permissions needed, recognizing that OOMOL handles the connection. The bundled read workflow is coherent; the material concerns are setup execution and undisclosed persistent agent changes. Remote installer behavior remains unverified.
The supplied command performs remote script execution for an apparent Oomol CLI installation, not Plasmic data searching or reading. Nothing in the supplied chunk establishes this installation as a supporting requirement for Plasmic access. The downloaded script's contents are not provided, so its further behavior cannot be determined.
The command pipes a mutable network response directly into Bash without independently verifying its integrity or authenticity; the PowerShell alternative has the same weakness. If the distribution endpoint or delivery infrastructure is compromised, following these instructions could execute attacker-controlled code with the invoking user's permissions, exposing local files and credentials even though Plasmic tokens are handled server-side.
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 missing-CLI fallback directs installation through remote script execution without explaining that this runs external code and may modify the local environment. Although conditional setup reduces exposure, a request to read Plasmic data does not itself constitute informed approval for installing software; this is a consent weakness in the same workflow flagged by SC2.
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