sandbox-sdk
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs agents to "fetch the relevant doc page or example first" and provides public URLs (e.g., https://developers.cloudflare.com/sandbox/ and the GitHub examples repo https://github.com/cloudflare/sandbox-sdk/tree/main/examples), which causes the agent to ingest third‑party public and user-generated content as part of its workflow.
Audit Metadata