Security audit
Security checks for vulnerabilities and agentic risk
The trial-search functions fit the stated purpose, but setup can run unverified installation code and introduce lasting agent changes without clear user control.
Review the dependency before installing. Require approval for software installation, use a reviewed and version-pinned CLI, and disable automatic skill synchronization if unwanted. Installer contents could not be inspected. OOMOL receives your search inputs, so avoid patient-identifying information. The artifacts support a setup and persistence concern, not a finding of malicious intent.
The supplied chunk executes an external installer rather than searching or reading ClinicalTrials.gov data. Nothing in the chunk establishes that this installation supports the declared functionality. The downloaded script's contents are not supplied, so its further actions cannot be determined.
The supplied code performs authentication rather than the declared ClinicalTrials.gov operations. Authentication could be a supporting implementation detail if its relationship to the declared service were established, but no such connection is present in this chunk.
Piping an HTTPS response directly into bash executes mutable remote content without a pinned version or independent integrity verification. A compromised distribution endpoint or malicious installer update could execute arbitrary commands with the agent process's permissions; the PowerShell alternative presents the same underlying 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
A missing dependency triggers instructions to execute a remote installer without first explaining its effects or obtaining explicit installation approval. This expands a read-only registry lookup into local code execution and potentially persistent system changes; the failure-only trigger reduces exposure but does not make those changes authorized.
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