eng-find-skills

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is to use the Skills CLI to search/install from the open agent skills ecosystem (e.g., via npx skills find / npx skills add), which can fetch and ingest outsider-authored public web/GitHub package content into the agent context as readable skill text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx skills add https://github.com/vercel-labs/skills --skill eng-find-skills" (and similar npx skills add owner/repo references), which fetches and installs remote code from the GitHub repo that can extend agent behavior and therefore directly control prompts or execute code at runtime.