Trust-boundary auditor - crafts an input (the agent's query OR crafted INDEXED CONTENT) that crosses a trust boundary or manipulates the agent-consumer. Beside the correctness-null family on the security axis - its oracle is a trust boundary, not functional correctness.
$curl -o .claude/agents/unbiddable-auditor.md https://raw.githubusercontent.com/jamie8johnson/cqs/HEAD/.claude/agents/unbiddable-auditor.mdInstalls into the current project.
Install unbiddable-auditor by running `curl -o .claude/agents/unbiddable-auditor.md https://raw.githubusercontent.com/jamie8johnson/cqs/HEAD/.claude/agents/unbiddable-auditor.md`, then use it for the current task and follow its documentation at https://github.com/jamie8johnson/cqs.