dt-app-dashboards
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes bash to execute local scripts (scripts/validate_dashboard.sh and scripts/deploy_dashboard.sh) and the dtctl CLI for DQL query validation. These operations are directly related to the skill's primary function of managing Dynatrace resources and align with standard developer tooling practices.
- [PROMPT_INJECTION]: The skill includes instructions to ingest and analyze external dashboard.json files, which introduces a potential surface for indirect prompt injection.
- Ingestion points: dashboard.json files processed in references/analyzing.md.
- Boundary markers: Absent during JSON data extraction and interpolation.
- Capability inventory: Execution of local shell scripts and DQL queries via CLI.
- Sanitization: No content validation or instruction filtering is performed on data extracted from the JSON files.
Audit Metadata