Security audit
Security checks for vulnerabilities and agentic risk
The Kickbox checks are appropriately scoped, but automatic setup executes unverified remote code and may introduce broader changes to your agent’s skills.
Review and preinstall a verified CLI release before allowing agent execution. Check its automatic skill synchronization settings, and submit only email addresses you intend OOMOL and Kickbox to process. The remote installers could not be inspected, so their exact installation effects remain uncertain.
The supplied command installs or bootstraps external software rather than searching or reading Kickbox data. Nothing in the chunk establishes that this installer is a supporting dependency for Kickbox access. The remote script's contents are not supplied, so its specific effects cannot be determined.
The supplied chunk only initiates authentication; it contains no Kickbox-specific operations or search/read functionality. Authentication can be a supporting implementation detail, but nothing here connects this login command to the declared Kickbox purpose.
The setup command executes a remotely downloaded script immediately, without a pinned version, independent integrity verification, or review; the PowerShell alternative has the same weakness. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent process's privileges, although the missing-CLI condition limits exposure.
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, including email verification, and labels untagged actions safe to run directly. Although it identifies Kickbox and OOMOL, it never warns that submitting an email address for verification discloses that potentially personal data to external services; a read-only action can still affect privacy.
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