Security audit
Security checks for vulnerabilities and agentic risk
LangSmith access is clearly explained, but setup can execute unverified internet code without asking you first.
Review and verify the CLI installer before authorizing setup, including any additional agent skills it installs or updates. Use a LangSmith API key limited to the intended work and understand that requests pass through OOMOL. The remote installation and authentication implementations are not bundled, so their exact system changes and credential storage remain unverified.
The supplied command accesses Oomol infrastructure and executes its installer. The description does not declare Oomol installation, and the supplied code establishes no connection between this installation and LangSmith functionality. The downloaded script is not provided, so its further behavior cannot be assessed.
The supplied code performs only a CLI login, with no visible connection to LangSmith or its data operations. Authentication could be a supporting implementation detail if oo were established as the LangSmith access mechanism, but the supplied material does not establish that relationship.
The command pipes a mutable remote script directly into bash without pinning or independently verifying its contents; the PowerShell alternative has the same problem. If the distribution endpoint or release pipeline is compromised, an agent following this fallback could execute attacker-controlled code with its local user's privileges, potentially exposing files and credentials.
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 a remote installer without first explaining system changes or obtaining installation-specific approval. Although conditional and relevant to setup, it expands a LangSmith data request into local code execution and software installation without a comparable consent safeguard to the one required for LangSmith writes.
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