dt-setup-openinference-migration
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes application source code and telemetry data (DQL) to determine migration logic, which represents an attack surface for indirect prompt injection if those sources are compromised.
- Ingestion points: Processes customer application code (Python) and queries existing span data in
references/detect-traceloop.md,references/ingestion-shape.md, andreferences/baseline-and-rollback.md. - Boundary markers: The skill implements mandatory "Stop and Ask" checkpoints before any application code modifications or tenant-wide configuration changes (e.g., OpenPipeline routing).
- Capability inventory: Possesses the capability to propose code diffs and modify Dynatrace platform settings via the
dtctlutility. - Sanitization: Explicitly instructs the agent never to print, log, or store credentials found during the migration process.
- [EXTERNAL_DOWNLOADS]: The skill references documentation, manifests, and configuration examples from vendor-controlled or well-known external repositories.
- Fetches instrumentation recipes from Dynatrace's official open-source GitHub repository.
- References the Dynatrace OTel collector manifest for component verification.
- Mentions the Bindplane agent (ObservIQ) as a well-known service alternative for collector-based metrics.
Audit Metadata