paw-mkt-influencer

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to use agent-browser to visit external platforms like TikTok, Instagram, and YouTube to search for user profiles and read public content bodies.

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

• Potentially malicious external URL detected (medium risk: 0.30). The configuration references a GitHub repository URL (https://github.com/vercel-labs/agent-browser) in references/shared-patterns.md specifically for installing the agent-browser skill via npx skills add, which constitutes an inbound operational runtime dependency fetch.