boilerplate-update

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly clones and reads a public GitHub repository ("git clone https://github.com/JUVOJustin/wordpress-plugin-boilerplate.git ./tmp/boilerplate-ref") and directs the agent to read files under tmp/boilerplate-ref/docs and use that upstream content to drive diffs and apply changes, so untrusted third‑party content can influence the agent's decisions and actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly runs a runtime git clone of https://github.com/JUVOJustin/wordpress-plugin-boilerplate.git and then instructs copying upstream .agents/skills and AI docs from tmp/boilerplate-ref (which can directly modify agent skills/prompts), so the fetched repository is used at runtime to supply content that can control agent prompts.