langfuse-prompt-migration

Warn

Audited by Snyk on Feb 15, 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 fetches prompt templates at runtime from the Langfuse host (e.g. https://cloud.langfuse.com) via langfuse.get_prompt()/create_prompt, so content served from that URL would directly control agent prompts and is a required runtime dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:37 PM