together-code-interpreter

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill makes runtime calls to the external API endpoint https://api.together.ai/tci/execute which executes arbitrary Python code on remote servers and is required for the skill to function, so the external URL directly executes code at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:06 PM