The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform cluster audits and interact with Kubernetes configurations. This capability is appropriate for the skill's stated purpose of auditing infrastructure.
[PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection because it is designed to ingest and analyze external, untrusted data such as Kubernetes manifests and Helm charts.
Ingestion points: Processes manifests, Helm values, and cluster configurations in Step 1 of the workflow.
Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore any natural language instructions that might be embedded within the configuration files (e.g., in metadata or comments).
Capability inventory: The skill has access to Bash for shell execution, Write for file system modification, and WebFetch for outbound network requests, which could be misused if a malicious instruction is successfully injected.
Sanitization: There is no evidence of content validation or filtering of the configuration data before it is processed by the agent.

kube-recon