x-cmd

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

• Third-party content exposure detected (high risk: 0.90). The skill's installation and usage docs explicitly instruct agents to fetch and run remote content (e.g., curl -fsSL https://get.x-cmd.com | sh, downloading binaries from https://github.com/x-cmd/release, and browsing https://x-cmd.com/llms.txt), so the agent would ingest untrusted third-party web content that could contain executable instructions influencing tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's installation guide explicitly recommends and documents an auto-install command that pipes remote code to the shell ("curl -fsSL https://get.x-cmd.com | sh"), which would fetch and execute remote code at runtime and is presented as a means to install the required x-cmd dependency.