observability-dashboard-creator

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (MEDIUM): The skill relies on executing local shell scripts (scripts/import-all-dashboards.sh, scripts/export-dashboards.sh, scripts/create-folder.sh) to perform its core functions. This behavior assumes the underlying scripts are secure and handled by a trusted environment.
  • [COMMAND_EXECUTION] (MEDIUM): The create-custom operation takes user-provided parameters (name, type, panels) and passes them to internal logic. If these parameters are interpolated into shell commands within scripts/create-custom.sh (implied by the dashboard creation logic) without rigorous sanitization, it could lead to command injection via shell metacharacters (e.g., ;, &&, |).
  • [DATA_EXFILTRATION] (LOW): The skill performs local network operations to localhost:3000 (Grafana API) and writes dashboard backups to the local filesystem (.observability/backups/). These are consistent with the skill's stated purpose but represent a local data access surface.
  • [PROMPT_INJECTION] (LOW): The skill's input parameters for dashboard creation could be used as a vector for indirect prompt injection if the resulting dashboard metadata is subsequently processed by an AI agent that interprets the dashboard names or panel descriptions as instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 04:38 AM