utoo

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "执行指令" section explicitly tells the agent to run curl -fsSL https://utoo.land/install | bash when the ut command is missing, which fetches and executes a script from a public third-party URL that can materially alter tool behavior and therefore exposes the agent to untrusted external content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime installation flow explicitly runs "curl -fsSL https://utoo.land/install | bash" if the utoo binary is missing, which fetches and executes remote code from https://utoo.land/install and is required to install the tool the skill depends on.