The Agent Skills Directory

[DATA_EXFILTRATION]: The skill provides the export_pcap tool which allows exporting captured Kubernetes traffic. The documentation acknowledges that this traffic can contain sensitive data such as PII and credentials within request/response payloads.
[COMMAND_EXECUTION]: The skill requires the kubectl binary in its metadata. It provides instructions for cluster-level operations including helm install and kubectl port-forward to manage the Kubeshark MCP server.
[PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by ingesting untrusted data from network traffic. 1. Ingestion points: Traffic payloads captured and analyzed via tools like capture_traffic and list_l4_flows. 2. Boundary markers: No explicit markers or warnings to ignore embedded instructions are present in the skill body. 3. Capability inventory: The skill has the ability to run kubectl commands and perform network queries against the MCP server. 4. Sanitization: There is no documented sanitization or filtering of captured traffic content before it is processed by the agent.

kubeshark-traffic