The Agent Skills Directory

[SAFE]: The skill's primary function is to facilitate the configuration and monitoring of Dynatrace alerting systems using standard DQL (Dynatrace Query Language) and the Dynatrace Settings API.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources by querying Davis events and problems from Dynatrace Grail. While these fields (such as event names or descriptions) could theoretically be populated by external systems through the Events API, the skill uses these mainly for summarization and report generation. The instructions do not involve executing commands derived from this data, effectively mitigating the risk of indirect instruction execution.
[DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials or sensitive file paths were detected. References to API keys or user UUIDs in the documentation use standard placeholders like <user-uuid> or SERVICE-XXXXXXXXXX, which is an acceptable practice.
[COMMAND_EXECUTION]: The skill uses DQL for data retrieval and Dynatrace-specific settings schemas for configuration. It does not spawn shell subprocesses or execute arbitrary system commands.

dt-alerting