muxy-cli
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill allows the agent to execute arbitrary shell commands in new or existing terminal sessions using
muxy session createandmuxy session sendas documented inSKILL.md. - [REMOTE_CODE_EXECUTION]: The skill supports executing commands on remote systems via SSH using the
--hostflag. Additionally, it mentions aninstall-skillscommand for installing new extensions. - [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to monitor and read terminal output, which may contain untrusted data that could influence the agent's behavior.
- Ingestion points:
muxy session read-screen,muxy session wait --text,muxy session search, andmuxy session history(SKILL.md). - Boundary markers: Absent; there are no instructions for the agent to distinguish between terminal output and legitimate instructions.
- Capability inventory: The skill can execute shell commands, send keystrokes, and manage Git worktrees (SKILL.md).
- Sanitization: Absent; the skill does not specify any filtering or sanitization of terminal output before it is processed by the agent.
Audit Metadata