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, and get-keys tools as described in SKILL.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
Risk Level
SAFE
Analyzed
Jul 9, 2026, 12:38 PM
Security Audit — agent-trust-hub — create-graph