Security audit
Security checks for vulnerabilities and agentic risk
The lookup workflow fits its purpose, but setup can execute unverified downloaded code without clear approval for the installation.
Install a reviewed, fixed CLI release yourself and require approval before any downloaded installer runs. Review its bundled-agent-skill behavior and understand that requests use your OOMOL-connected account and may consume credit. The remote installer contents remain unverified; no malicious behavior was established.
The supplied code performs remote script installation and execution, not Tianyancha searching or reading. Nothing in the chunk establishes that this installation supports the declared functionality. The downloaded script's contents and further effects are not provided, so those effects cannot be assessed.
The supplied chunk only invokes a CLI login command; it does not implement or invoke Tianyancha searching or reading. Authentication could be a supporting implementation detail, but nothing in this chunk establishes that this login supports Tianyancha access.
Piping the HTTPS installer directly into bash executes mutable remote content without a pinned version, integrity verification, or an inspection step. A compromised distribution endpoint or release could therefore execute attacker-controlled commands with the agent's local permissions; the legitimate dependency purpose and conditional setup reduce exposure but do not remove this supply-chain 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
The setup instructions direct the agent to execute downloaded shell or PowerShell code without explaining its effects or requiring explicit approval for local installation. Although limited to a missing-CLI failure, this expands a data-reading task into arbitrary code execution with the invoking user's privileges and could expose files or credentials if the installer is compromised.
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