otel-genai-instrumentation
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references standard OpenTelemetry instrumentation packages for Python and Node.js, such as
opentelemetry-instrumentation-openai-v2and@opentelemetry/instrumentation-openai. These are official or well-known community packages from the OpenTelemetry project. - [DATA_EXFILTRATION]: The skill facilitates the collection of LLM prompt and response content. It addresses the inherent risk of sensitive data or PII exposure by mandating a specific workflow where the agent must ask for user consent before implementation. It further provides code examples for PII filtering and payload truncation to mitigate exposure risks.
- [PROMPT_INJECTION]: The skill handles data from GenAI models which presents an indirect prompt injection surface. The instrumentation instructions focus on logging and telemetry rather than execution of this data, and the author includes guidance on sanitizing these payloads before they are recorded in traces.
Audit Metadata