marketing-psychology

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow can enter “Live Website URL Audit” mode and audit “the live page” provided by the user, which requires ingesting outsider-authored free text from an arbitrary public URL.

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

• Potentially malicious external URL detected (high risk: 0.90). The shared patterns instruct installing the agent-browser at runtime via "npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser", which fetches and executes remote code from that GitHub URL and is presented as a required runtime dependency.