Security audit
Security checks for vulnerabilities and agentic risk
The Neutrino workflow is coherent, but its setup can execute changing remote code and introduce additional agent skills without clearly explaining those effects.
Review the CLI installation and additional skill changes before enabling this skill. Use a verified CLI release and consider setting OO_SKILLS_SYNC_DISABLED=1 before invocation to prevent startup skill writes, as documented in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Submit only lookup data you are authorized to share with OOMOL and Neutrino. The sole bundled artifact was fully inspected; remote installer effects remain unverified, and no malicious behavior was established.
The supplied code performs remote installer execution, not a Neutrino API operation. No connection is shown between this installer and the declared API functionality, so it is not established as a supporting implementation detail. The downloaded script's contents and any additional effects are not visible in the supplied chunk.
The supplied code only initiates a CLI login; it does not perform a Neutrino API request or search/read data. Authentication could be a supporting implementation detail if tied to Neutrino API, but the supplied chunk establishes no such connection.
The installation command immediately executes remotely supplied code without pinning an artifact or independently verifying its integrity; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint could execute attacker-controlled code with the agent process's permissions, exposing local files and credentials. The missing-CLI condition reduces exposure, and enforced tool restrictions could block execution, but neither makes this installation instruction intrinsically safe.
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 workflow instructs the agent to execute connector actions with input payloads, which can include email addresses, phone numbers, or IP addresses sent through OOMOL to Neutrino. Although the services are identified, the skill does not warn about sharing potentially personal data and instead labels all untagged read actions as safe to run directly.
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