dt-obs-problems
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documentation and examples are focused on the intended use case of monitoring and analyzing system health within the Dynatrace environment. No evidence of prompt injection, data exfiltration, or unauthorized code execution was found.
- [PROMPT_INJECTION]: The skill's primary function involves analyzing external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: Telemetry data is ingested using
fetch dt.davis.problemsandfetch logsinSKILL.mdand related reference files. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the query patterns.
- Capability inventory: The skill provides read access to platform data via DQL but does not include tools for arbitrary command execution or external network communication.
- Sanitization: No specific methods for sanitizing the content of problem descriptions or log entries are described.
Audit Metadata