Caveat verdict
agent-swarm-dev-team
The multi-agent orchestration uses standard local tooling (tmux, git worktrees, gh CLI) for the documented dev-team automation purpose; no exfiltration or malicious behavior is present.
Automated static analysis — not a human review. Caveat 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.
Was this verdict right?
Thanks — recorded.