langfuse

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches prompt content at runtime from the Langfuse host (e.g., https://cloud.langfuse.com), using langfuse.get_prompt(...) and then compiling/using that prompt to drive model instructions, so external content from that URL directly controls agent prompts and is a required runtime dependency.