Security audit
Security checks for vulnerabilities and agentic risk
Figma operations have clear approval safeguards, but automatic setup can run unverified downloaded code without separate user approval.
Review and install a verified CLI release yourself before enabling this skill. Check its automatic skill synchronization and disable it if unwanted. Connecting Figma authorizes OOMOL to mediate access to your account; keep permissions limited and retain the skill's explicit approval requirements for changes and deletions. The concrete concern is uncontrolled setup and broader agent changes; the artifacts do not establish malicious intent.
The supplied command runs an Oomol installation script rather than performing any visible Figma operation. Although dependency installation can be a supporting implementation detail, the supplied chunk establishes no relationship between this installer and the declared Figma functionality. The downloaded script's contents are not supplied, so its additional behavior cannot be determined.
The command executes a mutable remote script immediately, without a pinned version, signature validation, or independent integrity check. If the distribution endpoint or its delivery pipeline is compromised, attacker-controlled code would run with the invoking account's privileges; HTTPS alone does not protect against compromise of the legitimate source.
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 recovery instructions direct the agent to execute remote shell or PowerShell code without explicit installation approval or disclosure of system changes. Dependency setup is legitimate here, but it crosses from Figma operations into local code execution with the agent's privileges; the missing-command condition limits exposure without making that transition safe.
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