Security audit
Security checks for vulnerabilities and agentic risk
The email-checking workflow is coherent, but its required CLI can persistently install other agent instructions without this skill disclosing that behavior.
Review the CLI dependency before installing. Use a reviewed release and, if you only want Abstract access, set OO_SKILLS_SYNC_DISABLED=1 before invoking oo to disable its documented skill synchronization. Email addresses submitted for validation pass through OOMOL to Abstract. The remote installers were unavailable for inspection, so their exact current behavior remains uncertain; no intentional malicious behavior was established.
The command executes an Oomol installation script and contains no Abstract API interaction or data-reading behavior. Remote code execution and installation from cli.oomol.com are not declared, and the supplied code provides no evidence that they support the stated Abstract functionality.
The supplied chunk performs only a CLI login operation; it contains no Abstract-specific requests or data-reading behavior. Authentication could support the declared purpose, but this chunk provides no evidence of that connection and instead implements a materially different standalone workflow.
The setup instructions pipe a mutable remote script directly into Bash without checking its contents, signature, or expected digest; the PowerShell alternative has the same problem. If the distribution endpoint or delivery chain is compromised, installation can execute attacker-controlled code with the invoking account's permissions, potentially exposing local files and credentials. Restricting setup to a missing-CLI error reduces exposure but does not remove 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 workflow instructs the agent to execute connector actions, and the available action validates an email address through Abstract using OOMOL. Although the providers are named, the skill never warns that the supplied email address will leave the user's environment and be transmitted through OOMOL to Abstract; calling untagged actions safe to run directly does not address this privacy impact.
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