create-graph
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill is designed to interact with a specific set of tools provided by the LaunchDarkly MCP server to manage dashboards and visualize data.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its interaction with external data sources.
- Ingestion points: The skill ingests untrusted data from the observability platform via the
get-dashboard,list-dashboards, andget-keystools as described inSKILL.md. - Boundary markers: The instructions do not define explicit delimiters or boundary markers for the data retrieved from these tools.
- Capability inventory: The agent's capabilities are limited to visualization and dashboard management tools (
create-graph,preview-graph,create-dashboard); it lacks access to the file system, arbitrary network operations, or subprocess execution. - Sanitization: No explicit sanitization or validation of retrieved metric names or dashboard configurations is defined in the instructions.
Audit Metadata