The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from external sources such as pod logs and Kubernetes resource definitions which may contain malicious instructions designed to influence agent behavior. \n- Ingestion points: Data is ingested via pod_logs and resources_get from the OpenShift cluster as part of the debugging workflow in SKILL.md. \n- Boundary markers: The skill instructs the agent to display logs and resource details within markdown code blocks. \n- Capability inventory: The skill has read access to cluster resources and pod logs via the openshift MCP server. \n- Sanitization: No specific input validation or sanitization rules are defined for the data retrieved from the cluster environment.

debug-pipeline