ClawAudit verdict
orchestrix-guide
The skill documents a tmux-based multi-agent orchestration workflow for Claude Code; network_in capability is consistent with its stated MCP server integration, and all commands shown are legitimate tmux/CLI operations.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
No red flags detected in static analysis.
Checked: 115 threat patterns · AST capability extraction · cross-zone compound shapes · permission integrity.
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Was this verdict right?
Thanks — recorded.