Security audit
Security checks for vulnerabilities and agentic risk
The PixelLab workflow is coherent, but its automatic setup can execute unverified downloaded code and introduce additional persistent agent skills.
Review setup before enabling this skill. Install a reviewed, fixed CLI release separately and retain approval for writes and deletions. To prevent additional agent skills being installed or refreshed, upstream documents setting OO_SKILLS_SYNC_DISABLED=1 before CLI use in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Requested content passes through OOMOL and PixelLab and may consume credits. The bundled instructions were fully inspected; external installer code and hosted connector behavior remain unverified.
The supplied code performs remote installer execution rather than PixelLab data operations. Although installation can be a supporting implementation detail, nothing supplied establishes this Oomol installer as a dependency of the declared PixelLab functionality. The downloaded script's further behavior cannot be determined from this chunk.
The only supplied command performs CLI login and contains no identifiable PixelLab integration or data operations. Authentication could support a PixelLab implementation, but no such connection is shown here; the supplied chunk's primary behavior therefore differs from the declared purpose.
The setup command pipes a mutable remote script directly into Bash without version pinning, integrity verification, or review; the PowerShell alternative uses the same download-and-execute pattern. Compromise of the installer distribution path could execute arbitrary code with the agent process's permissions, exposing local files and credentials. Installation is conditional on a missing CLI, which limits exposure but does not establish trust in the downloaded code.
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
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
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
## Resources
- PixelLab homepage: https://www.pixellab.ai/
- API documentation: https://api.pixellab.ai/v2/docs