The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it handles untrusted data that influences agent actions.
Ingestion points: The skill consumes user-provided application details and environment configurations to generate Kubernetes manifests and execute management commands (e.g., in the 'Example' section).
Boundary markers: None. The skill does not use delimiters or specific instructions to prevent the agent from following directions potentially embedded in the data it processes.
Capability inventory: The skill utilizes the Bash tool for kubectl operations and the Write tool for creating manifest files, which could be exploited if an attacker injects malicious YAML or command arguments.
Sanitization: There is no evidence of input validation, escaping, or sanitization logic to ensure user-supplied data doesn't contain malicious instructions or shell escapes.
[COMMAND_EXECUTION]: The skill relies on the execution of shell commands to perform its primary function of container orchestration.
Evidence: The skill defines several kubectl operations (apply, get, logs, scale, create secret) intended for execution via the Bash tool.

Container Orchestration