Security audit
Security checks for vulnerabilities and agentic risk
The openFDA searches are appropriately scoped, but missing software triggers instructions to execute an unverified online installer without explicit user approval.
Review and approve CLI installation separately before letting the agent perform setup. The remote installer and hosted service implementation were not verified. Queries pass through OOMOL, and account credentials and billing may be involved. No artifact-backed deception or exfiltration was found.
The supplied command performs remote script execution for an Oomol CLI installation, with no visible openFDA query or demonstrated connection to the declared purpose. This introduces an undeclared installation capability and accesses an unrelated resource. The downloaded script's contents and any further effects are not available for assessment.
The supplied chunk only performs a login operation rather than accessing openFDA data. Authentication could be a supporting implementation detail, but the code provides no evidence that this CLI or login supports the declared openFDA functionality. No credential theft or other additional behavior can be inferred from this command alone.
The command pipes a mutable HTTPS response directly into bash without verifying an independently trusted signature or digest. Compromise of the installation endpoint or its publishing pipeline could execute arbitrary code with the user's privileges; the PowerShell alternative has the same underlying risk, although the supplied content does not establish that either endpoint is malicious.
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 missing-CLI fallback instructs the agent to execute an installer without requiring approval or explaining its system changes. This crosses from reading public data into executing third-party code with the invoking user's privileges; the conditional trigger and oo-only tool declaration limit exposure but do not make the installation instructions safe.
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