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 bizevents and spans, including fields such as gen_ai.evaluation.input.question and gen_ai.evaluation.input.answer in SKILL.md and references/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
Risk Level
SAFE
Analyzed
Aug 14, 2026, 10:12 PM
Security Audit — agent-trust-hub — dt-obs-genai