langfuse

Warn

Audited by Snyk on Jun 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill initializes Langfuse with host="https://cloud.langfuse.com" and calls langfuse.get_prompt(...) at runtime, which fetches remote prompt content from that URL that is then compiled and used as LLM instructions, so https://cloud.langfuse.com is a runtime external dependency that directly controls prompts.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 22, 2026, 07:00 PM
Issues
1