The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the cx CLI tool to perform discovery (cx metrics search, cx search-fields), verification (cx metrics query, cx logs, cx spans), and deployment (cx dashboards create). These operations are consistent with the skill's stated purpose of managing Coralogix resources.
[DATA_EXPOSURE]: The skill reads local project files (e.g., README.md, meta.yaml, Dockerfile, and source code) to discover telemetry signals. This is a standard part of the dashboard creation workflow to ensure metrics and log fields are correctly identified.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from the local file system (source code, configuration files). However, the workflow includes human-in-the-loop checkpoints (Phase 3) where the user must approve the dashboard plan before JSON generation and deployment, which serves as a mitigation. The severity of this risk is considered low.
[SAFE]: The skill utilizes vendor-specific CLI tools and resources belonging to the author 'coralogix' to perform administrative tasks. All external operations are directed towards the Coralogix platform, and no unauthorized data exfiltration or credential theft patterns were found.

cx-create-dashboard