Security audit
Security checks for vulnerabilities and agentic risk
This financial-data skill needs review because setup executes unverified remote code and export uploads bypass its stated confirmation rules.
Review and approve the CLI installation separately, including its automatic skill synchronization. Require confirmation before export uploads and clarify their storage destination and retention. Ordinary queries fit the advertised purpose; the bundled text does not establish malicious intent, but external installer and connector implementations remain unverified.
The supplied chunk performs remote script execution rather than financial-data searching or reading. Although installing a CLI could be a supporting setup step, the supplied content establishes no connection between this installer and the declared service. The downloaded script's contents and any further effects are not visible.
Piping a mutable remote script directly into bash executes its contents without a separate review or artifact-verification step. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from supplying malicious code; this is the same installation risk identified by SQP-2, not an independent exploit.
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 export actions explicitly upload datasets to transit storage but lack the write tags that trigger user confirmation. This contradicts the blanket assurance that untagged actions are reads and could cause storage creation or external transfer without informed approval, although the described datasets are market data rather than private account records.
The missing-CLI fallback instructs the agent to execute remotely supplied shell or PowerShell code without explicit installation approval or integrity verification. If executed and the distribution channel is compromised, that code could modify the host or access files and credentials with the invoking user's privileges; the setup-only condition limits exposure but does not remove it.
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