Security audit
Security checks for vulnerabilities and agentic risk
The BlazeMeter reads fit the stated purpose, but automatic installation and undisclosed changes to other agent skills need review.
Review and approve a specific CLI release before allowing automatic setup, and confirm you trust OOMOL to mediate the connected account. Current CLI documentation provides OO_SKILLS_SYNC_DISABLED=1 to prevent startup writes to agent skill directories; verify support in your chosen release. [Publisher controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The remote installers could not be inspected, so their exact changes remain uncertain.
The declared purpose is reading BlazeMeter Functional data, whereas the supplied command executes an external installer. Nothing in the chunk establishes that this installer supports the declared functionality. Remote script execution is a materially different, undeclared capability; the downloaded script's further behavior cannot be determined from the supplied code.
Piping a mutable remote installation script directly into bash executes its contents without version pinning or integrity verification. If the distribution endpoint or its publishing infrastructure is compromised, the installer can execute attacker-controlled commands with the user's permissions; HTTPS alone does not protect against such compromise. The documented dependency explains the download's purpose 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
When the CLI is missing, the setup instructions direct the agent to execute downloaded shell or PowerShell code without first obtaining explicit installation approval or explaining host-level effects. This expands a read-only data task into arbitrary code execution with the invoking user's permissions; conditional execution limits exposure but does not establish user consent or script integrity.
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