Security audit
Security checks for vulnerabilities and agentic risk
The Alpaca data access fits the stated purpose, but automatic setup can execute unverified software and make broader changes to your agent environment.
Review the CLI installation separately and require approval before downloaded code runs or other agent skills change. Use a verified release, review its skill synchronization settings, and consider whether OOMOL should handle access to your financial account. The review concern is automatic setup and broader persistent changes; the artifact does not demonstrate malicious intent.
The supplied chunk performs no visible Alpaca search or data retrieval. Instead, it executes an external installer from an unrelated domain. This is a materially different operation from the declared read/search purpose, and the supplied code does not establish it as a supporting Alpaca implementation detail. The downloaded script's contents and further effects are unknown.
The supplied chunk performs only an authentication command; it contains no Alpaca-specific operations or data retrieval. Authentication could support a data-access skill, but the supplied content does not establish that this login is for Alpaca, so its demonstrated behavior is not adequately represented by the declared purpose.
Piping the HTTPS response directly into bash executes mutable remote code without version pinning, integrity verification, or prior inspection. A compromised installer host or release pipeline could execute attacker-controlled commands, exposing local files and credentials; the legitimate connector dependency 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 fallback instructs the agent to execute downloaded shell or PowerShell code without first explaining the system changes or obtaining explicit installation approval. Although triggered only when the CLI is missing, this can turn a read-only data request into arbitrary code execution with the agent process's permissions.
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