Security audit
Security checks for vulnerabilities and agentic risk
The text-analysis workflow fits its purpose, but unchecked installation and undisclosed changes to other agents’ skills need review.
Before use, install a verified, fixed CLI release yourself and review its persistent changes. The CLI documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup writes to agent skill directories; see its [environment options](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Submit only text you authorize OOMOL and Rosette to process. The complete bundled Markdown was inspected, but the remote installer remains unverified.
The supplied code performs remote software installation, not Rosette data searching or reading. Nothing in the supplied chunk establishes that this installer is a supporting dependency for the declared functionality. The downloaded script's further behavior is not visible.
The setup command pipes a mutable remote script directly into Bash without pinning a version, verifying integrity, or reviewing its contents; the PowerShell alternative has the same issue. Compromise of the installation endpoint or release infrastructure could execute attacker-controlled code with the agent process's permissions, although the command-not-found prerequisite limits exposure to setup scenarios.
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 workflow instructs the agent to submit action payloads through OOMOL to Rosette Text Analytics, potentially exposing personal or confidential document content. Although the skill identifies the connector, it does not warn about this data disclosure, and line 48 broadly characterizes untagged actions as safe to run directly.
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