skills/proompteng/lab/tailscale/Gen Agent Trust Hub

tailscale

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill executes tailscale diagnostic commands to troubleshoot network issues, which aligns with its primary purpose.
  • DATA_EXPOSURE (SAFE): Internal hostnames and a username are included in the documentation and scripts as configuration examples.
  • INDIRECT_PROMPT_INJECTION (LOW): 1. Ingestion points: scripts/tailscale-diag.sh accepts a HOST argument. 2. Boundary markers: None present. 3. Capability inventory: Execution of tailscale status/netcheck/ping. 4. Sanitization: The input is shell-quoted in the script but not validated against a whitelist.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM