dt-obs-azure
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of Markdown documentation and reference files that provide Dynatrace Query Language (DQL) templates. These templates are used to query and analyze Azure resource metadata and metrics already ingested into the Dynatrace platform.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for processing external data, such as Azure resource names and tags, which could potentially contain malicious instructions. However, the risk is mitigated by the restricted execution environment.
- Ingestion points: Azure resource names, tags, and configuration data ingested via Smartscape (e.g.,
SKILL.md,references/resource-management.md). - Boundary markers: Absent in the snippets, though the instructions guide the agent to use specific filters for scoping.
- Capability inventory: Operations are limited to read-only DQL queries (e.g.,
smartscapeNodes,summarize,timeseries). The skill contains no capabilities for file system modification, network exfiltration, or subprocess execution. - Sanitization: Relies on the underlying platform's DQL engine for query safety.
- [DATA_EXPOSURE]: No hardcoded credentials or sensitive file paths were found. The documentation uses standard placeholders (e.g.,
<SUBSCRIPTION_ID>,<RESOURCE_GROUP>) and non-sensitive example GUIDs. - [COMMAND_EXECUTION]: No shell commands or dynamic context injection patterns (
!command) were found in the instructions.
Audit Metadata