rancher-resource-troubleshooting
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as direct prompt injection, data exfiltration, or obfuscated code, were detected. The skill's structure and instructions are strictly focused on legitimate Kubernetes troubleshooting operations.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes untrusted data from Kubernetes logs and cluster events. This is an inherent risk for diagnostic tools and is considered a functional requirement for the primary purpose of the skill.
- Ingestion points: Cluster data retrieved via
mcp__rancher__kubernetes_logsandmcp__rancher__kubernetes_events. - Boundary markers: Absent; the skill passes the raw retrieved content to sub-agents for analysis without specific delimiters or isolation instructions.
- Capability inventory: Restricted to Kubernetes-specific management tools provided by the MCP (logs, events, describe, get).
- Sanitization: No explicit filtering or sanitization of log/event content is performed before analysis.
Audit Metadata