bun-api

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

• Third-party content exposure detected (high risk: 0.80). The skill documentation includes explicit runtime flows that fetch and ingest arbitrary HTTP content (e.g., File I/O "Read from URL" with Bun.file('https://example.com/data.json'), Bun.write('page.html', await fetch('https://example.com')), and the "Script Patterns → Data Pipeline" example using $curl -s https://api.example.com/data.json()), then parse and act on that data (store in DB, write files), which exposes the agent to untrusted third-party content that can influence subsequent actions.