LLM Tracing and Observability Setup

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill configures applications to send trace data, including prompt content, model responses, and metadata, to external observability backends (cloud.langfuse.com, oai.helicone.ai). These are well-known services used for LLM operations and debugging.
  • [EXTERNAL_DOWNLOADS]: Instructions include the installation of the langfuse package from public registries, which is the standard library for the associated observability service.
  • [PROMPT_INJECTION]: The provided implementation examples demonstrate passing unvalidated user input directly into LLM chain invocations and API calls (e.g., user_query, user_input). This pattern identifies a surface for indirect prompt injection where malicious instructions embedded in user data could influence the behavior of the instrumented model.
  • Ingestion points: generate_response and chain.invoke calls in SKILL.md accept raw string inputs.
  • Boundary markers: Absent in the provided code snippets.
  • Capability inventory: Instrumented functions perform network operations via LLM providers (OpenAI) and observability APIs.
  • Sanitization: No sanitization or input validation logic is included in the configuration templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:57 AM
Security Audit — agent-trust-hub — LLM Tracing and Observability Setup