The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the atmos CLI to perform validation of configurations, stacks, and components. These are standard operations for the tool's intended purpose.
[EXTERNAL_DOWNLOADS]: The skill fetches external JSON schemas from https://json.schemastore.org for validating GitHub Actions workflows. This is a well-known and reputable service for schema definitions.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill processes various Atmos configuration files (atmos.yaml), stack manifests, and component variables (input.vars) in SKILL.md and references/project-validation.md.
Boundary markers: No explicit natural language boundary markers or "ignore instructions" warnings are defined for the processed data; it relies on the internal parsing logic of the Atmos tool.
Capability inventory: The skill possesses the capability to execute shell commands (atmos) and perform network requests to download schemas.
Sanitization: Input data is sanitized and validated against structural rules (JSON Schema) and business logic (OPA/Rego) as defined in references/json-schema.md and references/opa-policies.md.

atmos-validation