maple-agent-tracing-openai-agents
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides standard shell commands for installing necessary dependencies and configuring environment variables (such as
OTEL_SERVICE_NAMEandOTEL_EXPORTER_OTLP_ENDPOINT). - [EXTERNAL_DOWNLOADS]: The instructions involve downloading standard OpenTelemetry and OpenInference packages from official registries (NPM and PyPI) to enable telemetry functionality within the agentic application.
- [DATA_EXFILTRATION]: The skill configures the application to export agent execution traces, including transcripts, model calls, and tool interactions, to the Maple service's ingestion endpoints (
ingest.maple.dev). This is the intended and documented functionality of the integration for observability purposes. - [SAFE]: The skill promotes secure credential management by advising against hardcoding API keys in client-side code and recommending the use of environment variables or secret managers. It also explicitly addresses data privacy by providing instructions for redacting sensitive content and PII using OpenTelemetry processors or bridge configuration settings.
Audit Metadata