debug-pod
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a well-defined debugging procedure using the 'openshift' MCP server to retrieve cluster information.
- [COMMAND_EXECUTION]: The skill recommends corrective 'oc' commands to the user. It does not execute these commands automatically, relying on user interaction as a security boundary.
- [DATA_EXFILTRATION]: While the skill retrieves pod logs and events which could contain sensitive data, it does so within the authenticated session and does not transmit data to unauthorized external endpoints.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface associated with its primary purpose. Ingestion points: Pod logs and event lists are retrieved via MCP in SKILL.md. Boundary markers: Information is presented in markdown blocks without explicit instructions to ignore embedded content. Capability inventory: Access is limited to read-only MCP tools and suggested CLI commands for manual user execution. Sanitization: Data retrieved from the cluster is not sanitized before display.
Audit Metadata