langfuse
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates integration with well-known observability and LLM services. All network operations target established domains (e.g., langfuse.com, openai.com), which are recognized as safe environments for telemetry and model interaction.
- [SAFE]: The skill uses appropriate placeholders for sensitive credentials. Code snippets initialize clients using 'pk-...' and 'sk-...' strings, encouraging users to provide their own keys rather than hardcoding actual secrets.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes external data from user messages and datasets for evaluation and tracing purposes.
- Ingestion points: User inputs in chat handlers and evaluation dataset items in SKILL.md.
- Boundary markers: None observed in the provided code examples.
- Capability inventory: Network communication with Langfuse and OpenAI APIs.
- Sanitization: Not present in the instructional code snippets.
Audit Metadata