dt-obs-genai
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and DQL templates for analyzing AI observability data within the Dynatrace platform. It does not perform any network operations, external downloads, or command executions.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by reading potentially untrusted data from observability spans and evaluation events.
- Ingestion points: Data is fetched via DQL from
bizeventsand spans, including fields such asgen_ai.evaluation.input.questionandgen_ai.evaluation.input.answerinSKILL.mdandreferences/evaluations.md. - Boundary markers: None identified in the provided DQL snippets.
- Capability inventory: Analysis is limited to data retrieval and visualization; the skill contains no capabilities for subprocess execution, file writes, or network requests.
- Sanitization: No explicit sanitization or filtering of the retrieved question/answer content was found.
Audit Metadata