multi-node-management
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of
homelab_nodeExec, a tool designed to run arbitrary commands on remote nodes. This capability allows the agent to perform unrestricted operations on the fleet, which could be exploited to execute malicious scripts or commands if the agent's context is compromised. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing external infrastructure data.
- Ingestion points: Untrusted data enters the agent context via the
homelab_inventorySynctool, which retrieves host lists and metadata from Ansible inventory files and Tailscale peer discovery. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the ingested inventory data are specified.
- Capability inventory: The agent has access to
homelab_nodeExec(arbitrary command execution) and various monitoring tools (homelab_nodeStatus,homelab_serviceHealth) across all configured nodes. - Sanitization: The skill does not describe any validation or escaping of the data fetched from Ansible or Tailscale before it is processed or used to target nodes.
Audit Metadata