xurl

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

• Third-party content exposure detected (medium risk: 0.30). The xurl CLI tool consumes posts, searches, mentions, and DMs from X/Twitter, which can contain outsider-authored free text read automatically into the agent workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill contains an installation command that fetches and executes a remote shell script from GitHub (curl -fsSL https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh | bash), which constitutes executing remote code at runtime.