manage-dashboards
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gcxcommand-line utility to interact with Grafana APIs. This involves executing subcommands to list, get, push, and delete resources, as well as managing local development servers for dashboard live-reloading. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Grafana instances that could contain untrusted instructions.
- Ingestion points: Untrusted data is ingested when the agent reads dashboard configurations via
gcx dashboards getorgcx resources pull, and when it performs visual analysis of PNG snapshots created bygcx dashboards snapshot. - Boundary markers: The instructions lack explicit delimiters or safety warnings to distinguish between dashboard data and operational instructions.
- Capability inventory: The agent possesses capabilities to execute shell commands (
gcx) and modify the local filesystem. - Sanitization: No sanitization or validation of the text content within dashboard titles, descriptions, or variables is performed before processing.
Audit Metadata