bun

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

• Third-party content exposure detected (high risk: 0.90). The skill documentation shows the agent can fetch and ingest arbitrary external content (e.g., fetch("https://api.example.com/data"), fetch("s3://my-bucket/file.txt"), Bun.file/S3 reads, and reading HTTP/WebSocket request bodies via Bun.serve and HTMLRewriter), which are untrusted third‑party/user-generated sources that the agent would read and interpret as part of its workflow.