xurl

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

• Third-party content exposure detected (medium risk: 0.30). The xurl CLI skill interacts with the X (Twitter) API, allowing the agent to read posts, timelines, mentions, and DMs, which are public or outsider-authored text sources that are automatically ingested into the runtime workflow.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation script downloaded via curl from GitHub uses an unpinned, mutable script payload that executes arbitrary remote code during setup, constituting a high-risk external dependency.