build-your-own-openclaw-agent-tutorial

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

• Third-party content exposure detected (low risk: 0.10). The tutorial demonstrates web search and webpage fetching tools (Step 6) that allow fetching arbitrary web pages and search results into the agent's context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an arbitrary external repository (https://github.com/czl9707/build-your-own-openclaw.git) and executing code and installation scripts from it, which introduces a weak/unknown/suspicious runtime external dependency.