agent-loop-orchestrator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes a triage step that “scans open issues, PRs, CI failures” (e.g., via /agent-loop:triage --scope current/all), which necessarily ingests outsider-authored free-form text like GitHub issue/PR bodies and comments into the agent’s LLM context for classification/dispatch.