herdr-agent-comms
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
herdrCLI to manage terminal panes, agent naming, and task dispatch. These operations are executed via Python'ssubprocess.runand Bash scripts, which is the primary and intended purpose of the skill. - [SAFE]: The skill implements significant security best practices, including fail-closed preflight checks that verify a target pane's status (idle, working, or blocked) before dispatching commands. This prevents tasks from being typed into unexpected UI elements like trust or permission dialogs. Additionally, the use of unique, multi-part completion markers ensures that the agent correctly identifies the end of its own task output without being misled by prompt echoes or stale transcripts.
Audit Metadata