The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were detected in the skill content. The instructions are purely informational and follow standard DevOps practices for configuration management.
[NO_CODE]: The skill consists exclusively of markdown documentation and configuration examples. No scripts, binaries, or automated tasks are present.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external YAML configuration files, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Atmos configuration files (e.g., atmos.yaml, auth.yaml).
Boundary markers: None explicitly defined in the skill instructions.
Capability inventory: Uses the atmos CLI tool to perform infrastructure actions (plan, deploy, describe).
Sanitization: No specific sanitization or validation steps for configuration content are provided in the skill.

atmos-profiles