netwhiz

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a variety of subcommands through the 'netwhiz' CLI, including those that modify system state such as 'netwhiz dns set' for changing name servers and 'netwhiz vpn connect' for establishing network tunnels.
  • [EXTERNAL_DOWNLOADS]: The skill references and suggests the installation of the 'netwhiz' utility from the author's repository ('lu-zhengda/tap/netwhiz') using Homebrew.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes potentially untrusted data. • Ingestion points: The 'target-host' argument and the outputs of commands like 'netwhiz info' or 'netwhiz scan'. • Boundary markers: No delimiters are used to isolate these inputs from the system prompt. • Capability inventory: The skill can execute any 'netwhiz' command via the Bash tool. • Sanitization: There is no evidence of input validation or output sanitization within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 03:29 AM