The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the dynamic context execution syntax to run date and kubectl config current-context when the skill is initialized. These commands are diagnostic and align with the skill's purpose of generating SRE and infrastructure documentation.
[COMMAND_EXECUTION]: The skill is designed to interact with infrastructure tools (kubectl, GCP CLI) and local configuration files (e.g., templates in ~/.config/opencode/). This behavior is consistent with the primary function of an operational runbook generator.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics and scenarios which could serve as a vector for indirect injection.
Ingestion points: Untrusted data enters the agent context through the Topic, Scope, and Optional input fields defined in SKILL.md.
Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore embedded commands within the input data.
Capability inventory: The skill has the capability to read codebase manifests and infrastructure configurations and write to the filesystem using the obsidian_append_content tool.
Sanitization: Absent. The skill does not explicitly specify sanitization or validation logic for the external content it processes during investigation tracks.

runbook