switchboard

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is explicitly designed to execute shell commands specified in a manifest YAML file. The run.sh script facilitates interactions with a local Switchboard server which manages these subprocess calls.
  • Evidence in SKILL.md (Supported action types) and run.sh (start/status/tail commands).
  • The allowed-tools list includes Bash, which is consistent with the skill's purpose of managing training scripts and tests.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:00 PM
Security Audit — agent-trust-hub — switchboard