Security audit
Security checks for vulnerabilities and agentic risk
The financial-data workflow is coherent, but its setup instructions can trigger unverified remote code execution without separate user approval.
Review before installing. Use an independently verified oo CLI installation and require approval before any downloaded installer runs. Expect queries to pass through OOMOL using your connected Investoday account. The artifact supports an installation-control concern, but does not establish malicious behavior; external installer effects remain unknown.
The supplied command performs remote script execution for an apparent CLI installation, not Investoday data searching or reading. The description does not disclose installation behavior or establish Oomol as a required supporting dependency. The downloaded script is not supplied, so its further effects cannot be determined.
The supplied code performs only authentication, rather than the declared Investoday search-and-read functionality. Authentication could be a supporting implementation detail, but this chunk provides no evidence that oo auth login authenticates to Investoday or supports an Investoday operation. The assessment is limited to the supplied chunk.
Piping an HTTPS response directly into bash executes mutable remote content without a pinned version, signature check, or opportunity to review the downloaded artifact. A compromised installer host or publishing pipeline could execute arbitrary commands and access files or credentials available to the agent; HTTPS alone does not protect against those compromises.
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 setup directs the agent to execute remotely downloaded shell or PowerShell code without explaining the arbitrary-code-execution risk or requesting approval for installation. Although limited to a missing-CLI condition, this can turn a financial-data lookup into execution of code with the agent process's local 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