langfuse
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS] (SAFE): The skill references standard and reputable Python libraries including langfuse, openai, and langchain. No installation of untrusted or remote scripts was detected.
- [DATA_EXFILTRATION] (SAFE): The skill demonstrates sending LLM trace data to the official Langfuse cloud endpoint (cloud.langfuse.com). This is the intended primary function of the tool. Credentials used in examples are generic placeholders (e.g., 'pk-...').
- [PROMPT_INJECTION] (SAFE): The instructions are purely technical and do not contain any attempt to bypass safety guidelines or override agent behavior.
- [COMMAND_EXECUTION] (SAFE): No subprocess calls, shell execution, or system-level commands are present in the provided snippets.
Audit Metadata