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
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 10:26 AM