The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review user-provided infrastructure configurations, such as Kubernetes manifests, Terraform modules, and CI/CD pipeline definitions. This ingestion of external data represents a potential surface for indirect prompt injection attacks.
Ingestion points: User-provided advisory questions and infrastructure artifacts (configs, manifests, pipelines) as described in SKILL.md and the reference files.
Boundary markers: The instructions do not define specific delimiters or "ignore" markers when the agent processes user-provided code for review.
Capability inventory: The skill relies on standard agent capabilities to provide text-based advice and generate infrastructure-as-code artifacts.
Sanitization: No explicit sanitization, validation, or escaping mechanisms are defined for the user-supplied data.

devops