Security audit
Security checks for vulnerabilities and agentic risk
The legal-search workflow is coherent, but setup can run unverified downloaded code and introduce additional agent skills without clearly disclosing those changes.
Review and install the CLI separately, verify its release provenance, and decide which additional agent skills it may install or synchronize. Send only necessary legal facts and remove unnecessary confidential details. The remote installers and live service implementation were not verified; no malicious behavior was established.
The supplied code runs a remote installer and contains no PKULaw search or data-reading operations. Nothing supplied establishes this installation as a necessary supporting implementation detail, and executing remote installation code is not disclosed in the declared purpose. The installer's downstream actions cannot be determined from this snippet.
Authentication can be a supporting implementation detail, but it is the entirety of the supplied code, with no demonstrated connection to PKULaw. As supplied, the code does not implement the declared purpose. This assessment does not imply credential theft or other unshown behavior.
The setup command pipes a mutable remote script directly into Bash without inspecting it or verifying a pinned version, signature, or independently trusted digest; the PowerShell alternative has the same problem. A compromised installer host or distribution pipeline could therefore execute attacker-controlled code with the agent's local privileges, exposing files and credentials. Restricting this to a missing-CLI error reduces exposure but does not make the execution mechanism 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 submit JSON payloads through OOMOL to PKULaw, including natural-language legal questions or fact patterns supported by the listed search actions. Although the connector is identified, the skill does not warn that submitted material leaves the user's environment and may contain confidential case details or personal information.
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