deno-sandbox
Warn
Audited by Snyk on Feb 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md (see "Running User Code Safely" and "AI Agent Tool Execution" examples) explicitly writes and executes user-submitted / toolCode inside the sandbox and parses/uses the sandbox output, meaning untrusted user-generated content is ingested and can materially influence agent actions.
Audit Metadata