Security audit
Security checks for vulnerabilities and agentic risk
The VerifiedEmail workflow is coherent, but automatic software installation and undisclosed changes to other agent skills warrant review.
Review and install the CLI separately using a fixed, verified release before enabling this skill. Review its automatic skill synchronization; current CLI documentation provides OO_SKILLS_SYNC_DISABLED=1 to disable startup skill writes. Connect only the intended account, expect verification inputs to pass through OOMOL, and check credit usage. The bundled artifact was fully inspected, but remote installers and server-side behavior remain unverified.
The supplied command executes a remote installer rather than searching or reading VerifiedEmail data. Nothing in the supplied code establishes this installation as a supporting dependency for the declared purpose. The downloaded script's contents and further effects are not shown.
The supplied chunk performs only an authentication operation; it contains no VerifiedEmail-specific access, search, or reading behavior. Authentication could be a supporting implementation detail if its connection to VerifiedEmail were established, but the supplied content does not establish that connection.
Piping a remote installer directly into bash executes mutable network-delivered code without inspecting or independently verifying it. HTTPS protects transport but does not protect against a compromised publisher or hosting infrastructure; the legitimate CLI dependency explains the download but does 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 fallback instructs the agent to execute downloaded shell or PowerShell code without an explicit installation approval step or an integrity-verification step. Although installing a required CLI is legitimate and conditional, a compromised installer source could execute arbitrary code with the invoking user's privileges.
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