bun-dev

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

• Third-party content exposure detected (high risk: 0.80). The skill’s examples explicitly show ingesting untrusted user-generated content (e.g., app.post('/upload') and other upload/download endpoints in examples/file-uploads.md, and WebSocket message handlers that JSON.parse incoming messages in references/server-patterns.md), so the agent would read and process arbitrary third‑party content provided by external users.