langfuse

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a comprehensive guide for using Langfuse, providing relevant code samples for Python and various integrations (LangChain, OpenAI).
  • [DATA_EXFILTRATION]: The code examples demonstrate sending telemetry data to https://cloud.langfuse.com. This is the intended and documented behavior for the observability service described in the skill.
  • [CREDENTIALS_UNSAFE]: The patterns include initialization code with public_key and secret_key fields; however, these use safe placeholders (e.g., pk-..., sk-...) rather than hardcoded secrets.
  • [EXTERNAL_DOWNLOADS]: The skill references established, well-known libraries such as langfuse, langchain, and openai. No suspicious or unverified dependencies are introduced.
  • [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety filters, override system instructions, or extract internal agent configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 02:41 AM