dt-app-dashboards

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard shell utilities including jq, sed, and grep to parse and transform dashboard JSON data during analysis and modification tasks.
  • [COMMAND_EXECUTION]: It invokes the dtctl CLI tool to perform query validation and execution against the Dynatrace platform, ensuring that DQL queries are functional before they are included in dashboards.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute local vendor-provided scripts, specifically scripts/validate_dashboard.sh and scripts/deploy_dashboard.sh, which automate the validation of JSON schema and the deployment of dashboard documents.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and executes DQL queries defined within potentially untrusted dashboard JSON files.
  • Ingestion points: External dashboard JSON files (e.g., dashboard.json) that are read and parsed by the agent using jq.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used when interpolating queries from data into the execution tools.
  • Capability inventory: Execution of arbitrary DQL queries via dtctl and deployment of dashboard configurations via shell scripts.
  • Sanitization: Validation is performed by a dedicated script (validate_dashboard.sh) and manual inspection, but no automated sanitization of DQL input is defined within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 05:16 AM